library(data.table)
library(lme4)
## Loading required package: Matrix
library(ggplot2)
# pseudo r-squared que vale para todo
r.squared <- function(m) {
lmfit <- lm(model.response(model.frame(m)) ~ fitted(m))
summary(lmfit)$r.squared
}
# unas medidas performance y goodness
model_performance <- function(m) {
# obs. vs fitted
df <- data.frame(fitted=fitted(m), response=model.response(model.frame(m)))
print(ggplot(df) + aes(fitted, response) + geom_point() + geom_smooth(method="lm"))
# pseudo r-squared
cat("pseudo-R2 =", r.squared(m))
}
model_assumptions <- function(m) {
# residuals vs fitted
df <- data.frame(fitted=fitted(m), residuals=residuals(m))
print(ggplot(df) + aes(fitted, residuals) + geom_point() + geom_smooth(method="lm"))
# residuals
qqnorm(residuals(m))
qqline(residuals(m))
}
source("exploratory/iu_features.R")
# quito socarxiv y psyarxiv de momento
df <- df[!repository %in% c("socarxiv", "psyarxiv")]
# quito papers donde el número de missing sea de más del 25% de los autores
df <- df[n_na < 0.25 * (n_na + n_male + n_female)]
# dissimilarity index (no lo uso aún)
df.diss <- df[, .(
diss = 0.5*sum(abs(n_male/sum(n_male) - n_female/sum(n_female)))
), by=.(repository, category, subcategory)]
# agregados por subcategoría, mes y covid
df.agg <- df[, .(
r_male = sum(n_male) / sum(n_male + n_female),
n_male = sum(n_male),
n_female = sum(n_female),
total = sum(n_male) + sum(n_female)
), by=.(repository, category, subcategory, covid, year, month)]
df.agg <- merge(df.agg, df.diss)
# quito observaciones con menos de 30 personas (en un mes)
df.agg <- df.agg[total > 30]
# covid era en realidad covidpaper
df.agg[, covidpaper := covid]
# llamamos (periodo) covid a febrero-mayo 2020
df.agg[, covid := year == 2020 & month > 2]
# me llevo la referencia de año y mes a 0
df.agg[, year := year - min(year)]
df.agg[, month := year*12 + month - 1]
En volumen, se crece un montón en número de autores:
ggplot(df.agg) + aes(month, total) + geom_col()
Esta es la distribución de la proporción de hombres, que parece bimodal (recordemos esto):
ggplot(df.agg) + aes(r_male, fill=covid) + geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Y parece que, overall, decrece la proporción de hombres:
ggplot(df.agg) + aes(month, r_male) + geom_boxplot(aes(group=month)) +
geom_smooth(method="lm")
## `geom_smooth()` using formula 'y ~ x'
Efectos de covid y covidpaper para el año 2020:
ggplot(df.agg[year == 3]) + aes(interaction(covid, covidpaper), r_male) +
geom_boxplot()
Efectos de covid y covidpaper para el año 2020 para las subcategorías que tienen papers COVID:
subcat_with_covidpaper <- unique(df.agg[covidpaper == TRUE]$subcategory)
ggplot(df.agg[subcategory %in% subcat_with_covidpaper]) +
aes(interaction(covid, covidpaper), r_male) +
geom_boxplot() + facet_grid(category~.)
La idea general es modelar el porcentaje de hombres en función de:
covid).covidpaper).Importante: usamos el número de autores (variable total) como pesos.
Empezamos por lo simple.
Primero vamos a ver qué podemos hacer con las categorías, que es lo más grueso:
fit_lm <- lm(
r_male ~ month + covid + covidpaper + category,
df.agg, weights=total)
Vamos a ver qué pinta tiene:
model_performance(fit_lm)
## `geom_smooth()` using formula 'y ~ x'
## pseudo-R2 = 0.6152669
Not bad, not good. Hay como dos clusters (¿recordáis la bimodal de arriba?, ¿puede ser eso?; en cualquier caso, está claro que las categorías no lo capturan).
model_assumptions(fit_lm)
## `geom_smooth()` using formula 'y ~ x'
Los he visto peores, pero podemos hacerlo mejor. Y finalmente:
summary(fit_lm)
##
## Call:
## lm(formula = r_male ~ month + covid + covidpaper + category,
## data = df.agg, weights = total)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -5.7083 -0.4090 0.1254 0.5840 3.4994
##
## Coefficients:
## Estimate Std. Error
## (Intercept) 6.814e-01 2.287e-03
## month -5.815e-04 6.858e-05
## covidTRUE 3.978e-03 1.979e-03
## covidpaperTRUE 1.306e-02 5.476e-03
## categoryComputer Science 1.639e-01 2.135e-03
## categoryEconomics 1.883e-01 1.070e-02
## categoryElectrical Engineering and Systems Science 1.603e-01 4.548e-03
## categoryHealth Sciences -2.569e-02 5.168e-03
## categoryMathematics 1.769e-01 2.524e-03
## categoryPhysics 1.650e-01 2.006e-03
## categoryStatistics 1.628e-01 3.486e-03
## t value Pr(>|t|)
## (Intercept) 297.891 <2e-16 ***
## month -8.478 <2e-16 ***
## covidTRUE 2.010 0.0445 *
## covidpaperTRUE 2.386 0.0171 *
## categoryComputer Science 76.750 <2e-16 ***
## categoryEconomics 17.602 <2e-16 ***
## categoryElectrical Engineering and Systems Science 35.237 <2e-16 ***
## categoryHealth Sciences -4.971 7e-07 ***
## categoryMathematics 70.088 <2e-16 ***
## categoryPhysics 82.231 <2e-16 ***
## categoryStatistics 46.711 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8612 on 3462 degrees of freedom
## Multiple R-squared: 0.7506, Adjusted R-squared: 0.7499
## F-statistic: 1042 on 10 and 3462 DF, p-value: < 2.2e-16
Coge 0.68 como intercept, lo que es raro raro (la media en 2017 es más alta, de alrededor de 0.82), y los efectos de covid y covidpaper son positivos (aumentan). Lo bueno es que hay muchas estrellicas. :)
Vamos a añadir las subcategorías:
fit_lm2 <- lm(
r_male ~ month + covid + covidpaper + subcategory,
df.agg, weights=total)
A ver:
model_performance(fit_lm2)
## `geom_smooth()` using formula 'y ~ x'
## pseudo-R2 = 0.8002547
Muuucho mejor. Está claro que las categorías son demasiado gruesas. Y los residuales:
model_assumptions(fit_lm2)
## `geom_smooth()` using formula 'y ~ x'
No están mal, pero se pueden mejorar. Finalmente:
summary(fit_lm2)
##
## Call:
## lm(formula = r_male ~ month + covid + covidpaper + subcategory,
## data = df.agg, weights = total)
##
## Weighted Residuals:
## Min 1Q Median 3Q Max
## -2.21653 -0.31031 0.02346 0.33057 2.89103
##
## Coefficients:
## Estimate
## (Intercept) 8.586e-01
## month -5.251e-04
## covidTRUE 2.792e-03
## covidpaperTRUE 1.302e-02
## subcategoryAdaptation and Self-Organizing Systems -1.640e-02
## subcategoryAddiction Medicine -2.319e-01
## subcategoryAlgebraic Geometry 1.080e-02
## subcategoryAlgebraic Topology 9.395e-03
## subcategoryAllergy and Immunology -2.548e-01
## subcategoryAnalysis of PDEs -1.809e-02
## subcategoryAnimal Behavior and Cognition -1.844e-01
## subcategoryApplications -7.477e-02
## subcategoryApplied Physics -1.995e-02
## subcategoryArtificial Intelligence -1.475e-02
## subcategoryAstrophysics of Galaxies -9.107e-02
## subcategoryAtmospheric and Oceanic Physics -7.857e-03
## subcategoryAtomic and Molecular Clusters -2.281e-02
## subcategoryAtomic Physics 1.778e-02
## subcategoryAudio and Speech Processing -1.833e-02
## subcategoryBiochemistry -1.664e-01
## subcategoryBioengineering -1.341e-01
## subcategoryBioinformatics -1.131e-01
## subcategoryBiological Physics -4.417e-02
## subcategoryBiomolecules -7.660e-02
## subcategoryBiophysics -1.050e-01
## subcategoryCancer Biology -2.140e-01
## subcategoryCardiovascular Medicine -1.062e-01
## subcategoryCategory Theory 5.785e-03
## subcategoryCell Behavior -1.010e-01
## subcategoryCell Biology -2.182e-01
## subcategoryChaotic Dynamics 1.514e-02
## subcategoryChemical Physics -1.081e-02
## subcategoryClassical Analysis and ODEs -4.367e-03
## subcategoryClassical Physics 2.060e-02
## subcategoryClinical Trials -2.474e-01
## subcategoryCombinatorics -2.698e-02
## subcategoryCommutative Algebra -2.599e-02
## subcategoryComplex Variables 2.402e-02
## subcategoryComputation 1.172e-02
## subcategoryComputation and Language -5.599e-02
## subcategoryComputational Complexity 3.698e-02
## subcategoryComputational Engineering, Finance, and Science 1.179e-02
## subcategoryComputational Finance 3.900e-02
## subcategoryComputational Geometry 1.996e-02
## subcategoryComputational Physics 2.515e-02
## subcategoryComputer Science and Game Theory -9.428e-05
## subcategoryComputer Vision and Pattern Recognition -2.722e-02
## subcategoryComputers and Society -7.996e-02
## subcategoryCosmology and Nongalactic Astrophysics -3.277e-02
## subcategoryCryptography and Security -8.358e-03
## subcategoryData Analysis, Statistics and Probability 5.217e-03
## subcategoryData Structures and Algorithms 2.054e-02
## subcategoryDatabases -2.523e-02
## subcategoryDermatology -1.574e-01
## subcategoryDevelopmental Biology -2.402e-01
## subcategoryDifferential Geometry 1.462e-02
## subcategoryDigital Libraries -6.944e-02
## subcategoryDiscrete Mathematics 1.395e-02
## subcategoryDisordered Systems and Neural Networks 1.033e-02
## subcategoryDistributed, Parallel, and Cluster Computing 6.835e-03
## subcategoryDynamical Systems -1.242e-02
## subcategoryEarth and Planetary Astrophysics -6.191e-02
## subcategoryEcology -1.650e-01
## subcategoryEconometrics 3.233e-02
## subcategoryEconomics -5.223e-03
## subcategoryEmergency Medicine -1.332e-01
## subcategoryEmerging Technologies 1.923e-02
## subcategoryEndocrinology (including Diabetes Mellitus and Metabolic Disease) -2.314e-01
## subcategoryEpidemiology -1.892e-01
## subcategoryEvolutionary Biology -1.578e-01
## subcategoryExactly Solvable and Integrable Systems -3.029e-03
## subcategoryFluid Dynamics 2.755e-02
## subcategoryFormal Languages and Automata Theory 2.357e-03
## subcategoryFunctional Analysis 6.153e-03
## subcategoryGastroenterology -1.989e-01
## subcategoryGeneral Economics -1.422e-02
## subcategoryGeneral Finance 1.606e-02
## subcategoryGeneral Literature 4.336e-02
## subcategoryGeneral Mathematics 2.371e-02
## subcategoryGeneral Physics 3.249e-02
## subcategoryGeneral Relativity and Quantum Cosmology 1.106e-02
## subcategoryGeneral Topology 1.676e-02
## subcategoryGenetic and Genomic Medicine -2.634e-01
## subcategoryGenetics -2.130e-01
## subcategoryGenomics -1.788e-01
## subcategoryGeometric Topology -2.478e-02
## subcategoryGeophysics -8.899e-03
## subcategoryGeriatric Medicine -4.088e-02
## subcategoryGraphics 6.636e-03
## subcategoryGroup Theory 5.034e-03
## subcategoryHardware Architecture 2.288e-02
## subcategoryHealth Economics -4.185e-02
## subcategoryHealth Informatics -1.369e-01
## subcategoryHealth Policy -1.777e-01
## subcategoryHealth Systems and Quality Improvement -2.068e-01
## subcategoryHematology -1.351e-01
## subcategoryHigh Energy Astrophysical Phenomena -4.120e-02
## subcategoryHigh Energy Physics - Experiment -2.383e-02
## subcategoryHigh Energy Physics - Lattice 5.297e-02
## subcategoryHigh Energy Physics - Phenomenology -4.117e-04
## subcategoryHigh Energy Physics - Theory 3.808e-02
## subcategoryHistory and Overview -2.321e-02
## subcategoryHistory and Philosophy of Physics 3.613e-02
## subcategoryHIV/AIDS -2.480e-01
## subcategoryHuman-Computer Interaction -7.984e-02
## subcategoryImage and Video Processing -3.274e-02
## subcategoryImmunology -2.366e-01
## subcategoryInfectious Diseases (except HIV/AIDS) -2.123e-01
## subcategoryInformation Retrieval -5.069e-02
## subcategoryInformation Theory -2.084e-02
## subcategoryInstrumentation and Detectors -4.746e-03
## subcategoryInstrumentation and Methods for Astrophysics -3.700e-02
## subcategoryIntensive Care and Critical Care Medicine -1.193e-01
## subcategoryK-Theory and Homology 4.583e-02
## subcategoryLogic 4.804e-02
## subcategoryLogic in Computer Science 2.615e-02
## subcategoryMachine Learning -3.734e-03
## subcategoryMaterials Science -2.492e-02
## subcategoryMathematical Finance -1.429e-02
## subcategoryMathematical Physics 4.016e-02
## subcategoryMathematical Software 3.915e-02
## subcategoryMedical Education -8.481e-02
## subcategoryMedical Physics -5.418e-02
## subcategoryMesoscale and Nanoscale Physics 5.368e-03
## subcategoryMethodology -4.983e-02
## subcategoryMetric Geometry 2.543e-02
## subcategoryMicrobiology -2.203e-01
## subcategoryMolecular Biology -2.041e-01
## subcategoryMolecular Networks -7.379e-02
## subcategoryMultiagent Systems 2.182e-03
## subcategoryMultimedia -4.221e-02
## subcategoryNephrology -2.355e-01
## subcategoryNetworking and Internet Architecture -6.775e-03
## subcategoryNeural and Evolutionary Computing 1.240e-02
## subcategoryNeurology -1.860e-01
## subcategoryNeurons and Cognition -6.842e-02
## subcategoryNeuroscience -1.793e-01
## subcategoryNuclear Experiment -2.607e-02
## subcategoryNuclear Theory -4.704e-03
## subcategoryNumber Theory 1.850e-02
## subcategoryNumerical Analysis -3.937e-03
## subcategoryNutrition -2.864e-01
## subcategoryObstetrics and Gynecology -4.172e-01
## subcategoryOccupational and Environmental Health -2.193e-01
## subcategoryOncology -2.191e-01
## subcategoryOperating Systems 4.299e-02
## subcategoryOperator Algebras 2.816e-02
## subcategoryOphthalmology -2.110e-01
## subcategoryOptics 1.396e-03
## subcategoryOptimization and Control 2.768e-03
## subcategoryOther Computer Science -2.097e-02
## subcategoryOther Condensed Matter 2.083e-02
## subcategoryOther Quantitative Biology -9.560e-02
## subcategoryOther Statistics -7.270e-02
## subcategoryOtolaryngology -7.187e-02
## subcategoryPaleontology -4.427e-02
## subcategoryPathology -2.275e-01
## subcategoryPattern Formation and Solitons 1.064e-02
## subcategoryPediatrics -3.002e-01
## subcategoryPerformance 1.320e-02
## subcategoryPharmacology and Therapeutics -1.899e-01
## subcategoryPharmacology and Toxicology -1.975e-01
## subcategoryPhysics and Society -2.547e-02
## subcategoryPhysics Education -1.397e-01
## subcategoryPhysiology -2.161e-01
## subcategoryPlant Biology -1.936e-01
## subcategoryPlasma Physics 2.798e-02
## subcategoryPopular Physics -5.809e-02
## subcategoryPopulations and Evolution -7.796e-02
## subcategoryPortfolio Management -3.625e-02
## subcategoryPricing of Securities 8.302e-02
## subcategoryPrimary Care Research -2.276e-01
## subcategoryProbability 1.016e-02
## subcategoryProgramming Languages 3.357e-02
## subcategoryPsychiatry and Clinical Psychology -2.434e-01
## subcategoryPublic and Global Health -2.302e-01
## subcategoryQuantitative Methods -8.585e-02
## subcategoryQuantum Algebra 1.857e-03
## subcategoryQuantum Gases 2.231e-02
## subcategoryQuantum Physics 1.482e-02
## subcategoryRadiology and Imaging -1.573e-01
## subcategoryRehabilitation Medicine and Physical Therapy -2.793e-01
## subcategoryRepresentation Theory -1.796e-02
## subcategoryRespiratory Medicine -1.760e-01
## subcategoryRheumatology -2.791e-01
## subcategoryRings and Algebras -3.891e-02
## subcategoryRisk Management -9.479e-03
## subcategoryRobotics 1.247e-02
## subcategoryScientific Communication and Education -2.784e-01
## subcategorySexual and Reproductive Health -4.340e-01
## subcategorySignal Processing -1.957e-02
## subcategorySocial and Information Networks -4.321e-02
## subcategorySoft Condensed Matter -1.896e-02
## subcategorySoftware Engineering -2.854e-03
## subcategorySolar and Stellar Astrophysics -7.034e-02
## subcategorySound -1.348e-02
## subcategorySpace Physics -2.448e-02
## subcategorySpectral Theory 6.502e-03
## subcategorySports Medicine -6.391e-02
## subcategoryStatistical Finance 3.257e-03
## subcategoryStatistical Mechanics 3.434e-02
## subcategoryStatistics Theory -2.578e-02
## subcategoryStrongly Correlated Electrons 1.497e-02
## subcategorySubcellular Processes -7.617e-02
## subcategorySuperconductivity -8.860e-04
## subcategorySurgery -1.248e-01
## subcategorySymbolic Computation 2.322e-02
## subcategorySymplectic Geometry 1.018e-02
## subcategorySynthetic Biology -1.429e-01
## subcategorySystems and Control 1.370e-02
## subcategorySystems Biology -1.297e-01
## subcategoryTheoretical Economics 5.131e-02
## subcategoryTissues and Organs -1.312e-01
## subcategoryTrading and Market Microstructure 3.232e-02
## subcategoryZoology -1.661e-01
## Std. Error
## (Intercept) 1.075e-02
## month 3.958e-05
## covidTRUE 1.138e-03
## covidpaperTRUE 3.445e-03
## subcategoryAdaptation and Self-Organizing Systems 1.582e-02
## subcategoryAddiction Medicine 5.841e-02
## subcategoryAlgebraic Geometry 1.184e-02
## subcategoryAlgebraic Topology 1.370e-02
## subcategoryAllergy and Immunology 3.120e-02
## subcategoryAnalysis of PDEs 1.141e-02
## subcategoryAnimal Behavior and Cognition 1.470e-02
## subcategoryApplications 1.204e-02
## subcategoryApplied Physics 1.141e-02
## subcategoryArtificial Intelligence 1.117e-02
## subcategoryAstrophysics of Galaxies 1.099e-02
## subcategoryAtmospheric and Oceanic Physics 1.531e-02
## subcategoryAtomic and Molecular Clusters 1.973e-02
## subcategoryAtomic Physics 1.224e-02
## subcategoryAudio and Speech Processing 1.242e-02
## subcategoryBiochemistry 1.183e-02
## subcategoryBioengineering 1.258e-02
## subcategoryBioinformatics 1.131e-02
## subcategoryBiological Physics 1.258e-02
## subcategoryBiomolecules 1.645e-02
## subcategoryBiophysics 1.201e-02
## subcategoryCancer Biology 1.151e-02
## subcategoryCardiovascular Medicine 1.964e-02
## subcategoryCategory Theory 1.593e-02
## subcategoryCell Behavior 1.928e-02
## subcategoryCell Biology 1.142e-02
## subcategoryChaotic Dynamics 1.488e-02
## subcategoryChemical Physics 1.192e-02
## subcategoryClassical Analysis and ODEs 1.300e-02
## subcategoryClassical Physics 1.558e-02
## subcategoryClinical Trials 3.046e-02
## subcategoryCombinatorics 1.139e-02
## subcategoryCommutative Algebra 1.446e-02
## subcategoryComplex Variables 1.380e-02
## subcategoryComputation 1.377e-02
## subcategoryComputation and Language 1.116e-02
## subcategoryComputational Complexity 1.383e-02
## subcategoryComputational Engineering, Finance, and Science 1.481e-02
## subcategoryComputational Finance 2.633e-02
## subcategoryComputational Geometry 1.443e-02
## subcategoryComputational Physics 1.182e-02
## subcategoryComputer Science and Game Theory 1.338e-02
## subcategoryComputer Vision and Pattern Recognition 1.090e-02
## subcategoryComputers and Society 1.199e-02
## subcategoryCosmology and Nongalactic Astrophysics 1.119e-02
## subcategoryCryptography and Security 1.149e-02
## subcategoryData Analysis, Statistics and Probability 1.391e-02
## subcategoryData Structures and Algorithms 1.189e-02
## subcategoryDatabases 1.306e-02
## subcategoryDermatology 7.788e-02
## subcategoryDevelopmental Biology 1.214e-02
## subcategoryDifferential Geometry 1.210e-02
## subcategoryDigital Libraries 1.574e-02
## subcategoryDiscrete Mathematics 1.322e-02
## subcategoryDisordered Systems and Neural Networks 1.306e-02
## subcategoryDistributed, Parallel, and Cluster Computing 1.169e-02
## subcategoryDynamical Systems 1.193e-02
## subcategoryEarth and Planetary Astrophysics 1.128e-02
## subcategoryEcology 1.194e-02
## subcategoryEconometrics 1.802e-02
## subcategoryEconomics 1.850e-02
## subcategoryEmergency Medicine 3.659e-02
## subcategoryEmerging Technologies 1.476e-02
## subcategoryEndocrinology (including Diabetes Mellitus and Metabolic Disease) 3.213e-02
## subcategoryEpidemiology 1.170e-02
## subcategoryEvolutionary Biology 1.181e-02
## subcategoryExactly Solvable and Integrable Systems 1.701e-02
## subcategoryFluid Dynamics 1.198e-02
## subcategoryFormal Languages and Automata Theory 1.616e-02
## subcategoryFunctional Analysis 1.233e-02
## subcategoryGastroenterology 2.499e-02
## subcategoryGeneral Economics 1.943e-02
## subcategoryGeneral Finance 2.449e-02
## subcategoryGeneral Literature 7.608e-02
## subcategoryGeneral Mathematics 3.528e-02
## subcategoryGeneral Physics 2.039e-02
## subcategoryGeneral Relativity and Quantum Cosmology 1.128e-02
## subcategoryGeneral Topology 1.976e-02
## subcategoryGenetic and Genomic Medicine 1.487e-02
## subcategoryGenetics 1.131e-02
## subcategoryGenomics 1.119e-02
## subcategoryGeometric Topology 1.320e-02
## subcategoryGeophysics 1.450e-02
## subcategoryGeriatric Medicine 7.217e-02
## subcategoryGraphics 1.465e-02
## subcategoryGroup Theory 1.310e-02
## subcategoryHardware Architecture 1.593e-02
## subcategoryHealth Economics 4.790e-02
## subcategoryHealth Informatics 1.893e-02
## subcategoryHealth Policy 3.059e-02
## subcategoryHealth Systems and Quality Improvement 2.901e-02
## subcategoryHematology 5.882e-02
## subcategoryHigh Energy Astrophysical Phenomena 1.121e-02
## subcategoryHigh Energy Physics - Experiment 1.167e-02
## subcategoryHigh Energy Physics - Lattice 1.303e-02
## subcategoryHigh Energy Physics - Phenomenology 1.111e-02
## subcategoryHigh Energy Physics - Theory 1.119e-02
## subcategoryHistory and Overview 2.467e-02
## subcategoryHistory and Philosophy of Physics 2.276e-02
## subcategoryHIV/AIDS 3.750e-02
## subcategoryHuman-Computer Interaction 1.219e-02
## subcategoryImage and Video Processing 1.156e-02
## subcategoryImmunology 1.165e-02
## subcategoryInfectious Diseases (except HIV/AIDS) 1.187e-02
## subcategoryInformation Retrieval 1.216e-02
## subcategoryInformation Theory 1.102e-02
## subcategoryInstrumentation and Detectors 1.174e-02
## subcategoryInstrumentation and Methods for Astrophysics 1.133e-02
## subcategoryIntensive Care and Critical Care Medicine 2.011e-02
## subcategoryK-Theory and Homology 1.894e-02
## subcategoryLogic 1.418e-02
## subcategoryLogic in Computer Science 1.287e-02
## subcategoryMachine Learning 1.081e-02
## subcategoryMaterials Science 1.101e-02
## subcategoryMathematical Finance 2.010e-02
## subcategoryMathematical Physics 1.114e-02
## subcategoryMathematical Software 2.087e-02
## subcategoryMedical Education 7.441e-02
## subcategoryMedical Physics 1.334e-02
## subcategoryMesoscale and Nanoscale Physics 1.105e-02
## subcategoryMethodology 1.188e-02
## subcategoryMetric Geometry 1.466e-02
## subcategoryMicrobiology 1.115e-02
## subcategoryMolecular Biology 1.183e-02
## subcategoryMolecular Networks 1.783e-02
## subcategoryMultiagent Systems 1.385e-02
## subcategoryMultimedia 1.434e-02
## subcategoryNephrology 4.593e-02
## subcategoryNetworking and Internet Architecture 1.170e-02
## subcategoryNeural and Evolutionary Computing 1.206e-02
## subcategoryNeurology 1.629e-02
## subcategoryNeurons and Cognition 1.292e-02
## subcategoryNeuroscience 1.098e-02
## subcategoryNuclear Experiment 1.275e-02
## subcategoryNuclear Theory 1.197e-02
## subcategoryNumber Theory 1.201e-02
## subcategoryNumerical Analysis 1.132e-02
## subcategoryNutrition 5.527e-02
## subcategoryObstetrics and Gynecology 5.959e-02
## subcategoryOccupational and Environmental Health 2.720e-02
## subcategoryOncology 1.640e-02
## subcategoryOperating Systems 3.679e-02
## subcategoryOperator Algebras 1.507e-02
## subcategoryOphthalmology 3.970e-02
## subcategoryOptics 1.121e-02
## subcategoryOptimization and Control 1.134e-02
## subcategoryOther Computer Science 2.620e-02
## subcategoryOther Condensed Matter 1.514e-02
## subcategoryOther Quantitative Biology 4.812e-02
## subcategoryOther Statistics 3.016e-02
## subcategoryOtolaryngology 5.628e-02
## subcategoryPaleontology 7.981e-02
## subcategoryPathology 1.510e-02
## subcategoryPattern Formation and Solitons 1.554e-02
## subcategoryPediatrics 3.346e-02
## subcategoryPerformance 1.522e-02
## subcategoryPharmacology and Therapeutics 3.134e-02
## subcategoryPharmacology and Toxicology 1.422e-02
## subcategoryPhysics and Society 1.216e-02
## subcategoryPhysics Education 1.947e-02
## subcategoryPhysiology 1.357e-02
## subcategoryPlant Biology 1.205e-02
## subcategoryPlasma Physics 1.312e-02
## subcategoryPopular Physics 3.777e-02
## subcategoryPopulations and Evolution 1.298e-02
## subcategoryPortfolio Management 4.872e-02
## subcategoryPricing of Securities 4.295e-02
## subcategoryPrimary Care Research 5.768e-02
## subcategoryProbability 1.154e-02
## subcategoryProgramming Languages 1.392e-02
## subcategoryPsychiatry and Clinical Psychology 1.668e-02
## subcategoryPublic and Global Health 1.428e-02
## subcategoryQuantitative Methods 1.266e-02
## subcategoryQuantum Algebra 1.447e-02
## subcategoryQuantum Gases 1.226e-02
## subcategoryQuantum Physics 1.100e-02
## subcategoryRadiology and Imaging 2.023e-02
## subcategoryRehabilitation Medicine and Physical Therapy 3.235e-02
## subcategoryRepresentation Theory 1.269e-02
## subcategoryRespiratory Medicine 2.096e-02
## subcategoryRheumatology 3.130e-02
## subcategoryRings and Algebras 1.365e-02
## subcategoryRisk Management 3.012e-02
## subcategoryRobotics 1.147e-02
## subcategoryScientific Communication and Education 1.849e-02
## subcategorySexual and Reproductive Health 5.210e-02
## subcategorySignal Processing 1.142e-02
## subcategorySocial and Information Networks 1.182e-02
## subcategorySoft Condensed Matter 1.177e-02
## subcategorySoftware Engineering 1.237e-02
## subcategorySolar and Stellar Astrophysics 1.117e-02
## subcategorySound 1.245e-02
## subcategorySpace Physics 1.472e-02
## subcategorySpectral Theory 1.530e-02
## subcategorySports Medicine 6.638e-02
## subcategoryStatistical Finance 2.355e-02
## subcategoryStatistical Mechanics 1.161e-02
## subcategoryStatistics Theory 1.163e-02
## subcategoryStrongly Correlated Electrons 1.132e-02
## subcategorySubcellular Processes 2.739e-02
## subcategorySuperconductivity 1.186e-02
## subcategorySurgery 5.373e-02
## subcategorySymbolic Computation 2.229e-02
## subcategorySymplectic Geometry 1.633e-02
## subcategorySynthetic Biology 1.541e-02
## subcategorySystems and Control 1.131e-02
## subcategorySystems Biology 1.239e-02
## subcategoryTheoretical Economics 2.622e-02
## subcategoryTissues and Organs 1.810e-02
## subcategoryTrading and Market Microstructure 3.992e-02
## subcategoryZoology 2.140e-02
## t value
## (Intercept) 79.875
## month -13.264
## covidTRUE 2.453
## covidpaperTRUE 3.780
## subcategoryAdaptation and Self-Organizing Systems -1.037
## subcategoryAddiction Medicine -3.969
## subcategoryAlgebraic Geometry 0.912
## subcategoryAlgebraic Topology 0.686
## subcategoryAllergy and Immunology -8.166
## subcategoryAnalysis of PDEs -1.585
## subcategoryAnimal Behavior and Cognition -12.546
## subcategoryApplications -6.209
## subcategoryApplied Physics -1.749
## subcategoryArtificial Intelligence -1.320
## subcategoryAstrophysics of Galaxies -8.284
## subcategoryAtmospheric and Oceanic Physics -0.513
## subcategoryAtomic and Molecular Clusters -1.156
## subcategoryAtomic Physics 1.452
## subcategoryAudio and Speech Processing -1.476
## subcategoryBiochemistry -14.061
## subcategoryBioengineering -10.655
## subcategoryBioinformatics -9.998
## subcategoryBiological Physics -3.511
## subcategoryBiomolecules -4.656
## subcategoryBiophysics -8.741
## subcategoryCancer Biology -18.598
## subcategoryCardiovascular Medicine -5.406
## subcategoryCategory Theory 0.363
## subcategoryCell Behavior -5.240
## subcategoryCell Biology -19.118
## subcategoryChaotic Dynamics 1.017
## subcategoryChemical Physics -0.907
## subcategoryClassical Analysis and ODEs -0.336
## subcategoryClassical Physics 1.322
## subcategoryClinical Trials -8.120
## subcategoryCombinatorics -2.368
## subcategoryCommutative Algebra -1.797
## subcategoryComplex Variables 1.740
## subcategoryComputation 0.852
## subcategoryComputation and Language -5.016
## subcategoryComputational Complexity 2.675
## subcategoryComputational Engineering, Finance, and Science 0.796
## subcategoryComputational Finance 1.481
## subcategoryComputational Geometry 1.383
## subcategoryComputational Physics 2.127
## subcategoryComputer Science and Game Theory -0.007
## subcategoryComputer Vision and Pattern Recognition -2.498
## subcategoryComputers and Society -6.667
## subcategoryCosmology and Nongalactic Astrophysics -2.928
## subcategoryCryptography and Security -0.727
## subcategoryData Analysis, Statistics and Probability 0.375
## subcategoryData Structures and Algorithms 1.727
## subcategoryDatabases -1.932
## subcategoryDermatology -2.022
## subcategoryDevelopmental Biology -19.785
## subcategoryDifferential Geometry 1.209
## subcategoryDigital Libraries -4.412
## subcategoryDiscrete Mathematics 1.055
## subcategoryDisordered Systems and Neural Networks 0.791
## subcategoryDistributed, Parallel, and Cluster Computing 0.585
## subcategoryDynamical Systems -1.041
## subcategoryEarth and Planetary Astrophysics -5.490
## subcategoryEcology -13.827
## subcategoryEconometrics 1.794
## subcategoryEconomics -0.282
## subcategoryEmergency Medicine -3.642
## subcategoryEmerging Technologies 1.303
## subcategoryEndocrinology (including Diabetes Mellitus and Metabolic Disease) -7.202
## subcategoryEpidemiology -16.168
## subcategoryEvolutionary Biology -13.366
## subcategoryExactly Solvable and Integrable Systems -0.178
## subcategoryFluid Dynamics 2.300
## subcategoryFormal Languages and Automata Theory 0.146
## subcategoryFunctional Analysis 0.499
## subcategoryGastroenterology -7.961
## subcategoryGeneral Economics -0.732
## subcategoryGeneral Finance 0.656
## subcategoryGeneral Literature 0.570
## subcategoryGeneral Mathematics 0.672
## subcategoryGeneral Physics 1.593
## subcategoryGeneral Relativity and Quantum Cosmology 0.980
## subcategoryGeneral Topology 0.848
## subcategoryGenetic and Genomic Medicine -17.719
## subcategoryGenetics -18.832
## subcategoryGenomics -15.974
## subcategoryGeometric Topology -1.878
## subcategoryGeophysics -0.614
## subcategoryGeriatric Medicine -0.567
## subcategoryGraphics 0.453
## subcategoryGroup Theory 0.384
## subcategoryHardware Architecture 1.436
## subcategoryHealth Economics -0.874
## subcategoryHealth Informatics -7.231
## subcategoryHealth Policy -5.809
## subcategoryHealth Systems and Quality Improvement -7.129
## subcategoryHematology -2.298
## subcategoryHigh Energy Astrophysical Phenomena -3.677
## subcategoryHigh Energy Physics - Experiment -2.042
## subcategoryHigh Energy Physics - Lattice 4.065
## subcategoryHigh Energy Physics - Phenomenology -0.037
## subcategoryHigh Energy Physics - Theory 3.404
## subcategoryHistory and Overview -0.941
## subcategoryHistory and Philosophy of Physics 1.587
## subcategoryHIV/AIDS -6.614
## subcategoryHuman-Computer Interaction -6.549
## subcategoryImage and Video Processing -2.833
## subcategoryImmunology -20.303
## subcategoryInfectious Diseases (except HIV/AIDS) -17.895
## subcategoryInformation Retrieval -4.168
## subcategoryInformation Theory -1.891
## subcategoryInstrumentation and Detectors -0.404
## subcategoryInstrumentation and Methods for Astrophysics -3.266
## subcategoryIntensive Care and Critical Care Medicine -5.935
## subcategoryK-Theory and Homology 2.419
## subcategoryLogic 3.388
## subcategoryLogic in Computer Science 2.032
## subcategoryMachine Learning -0.345
## subcategoryMaterials Science -2.264
## subcategoryMathematical Finance -0.711
## subcategoryMathematical Physics 3.606
## subcategoryMathematical Software 1.876
## subcategoryMedical Education -1.140
## subcategoryMedical Physics -4.060
## subcategoryMesoscale and Nanoscale Physics 0.486
## subcategoryMethodology -4.194
## subcategoryMetric Geometry 1.734
## subcategoryMicrobiology -19.763
## subcategoryMolecular Biology -17.253
## subcategoryMolecular Networks -4.139
## subcategoryMultiagent Systems 0.158
## subcategoryMultimedia -2.943
## subcategoryNephrology -5.127
## subcategoryNetworking and Internet Architecture -0.579
## subcategoryNeural and Evolutionary Computing 1.028
## subcategoryNeurology -11.418
## subcategoryNeurons and Cognition -5.296
## subcategoryNeuroscience -16.325
## subcategoryNuclear Experiment -2.045
## subcategoryNuclear Theory -0.393
## subcategoryNumber Theory 1.541
## subcategoryNumerical Analysis -0.348
## subcategoryNutrition -5.182
## subcategoryObstetrics and Gynecology -7.002
## subcategoryOccupational and Environmental Health -8.060
## subcategoryOncology -13.354
## subcategoryOperating Systems 1.169
## subcategoryOperator Algebras 1.868
## subcategoryOphthalmology -5.315
## subcategoryOptics 0.124
## subcategoryOptimization and Control 0.244
## subcategoryOther Computer Science -0.800
## subcategoryOther Condensed Matter 1.376
## subcategoryOther Quantitative Biology -1.987
## subcategoryOther Statistics -2.411
## subcategoryOtolaryngology -1.277
## subcategoryPaleontology -0.555
## subcategoryPathology -15.068
## subcategoryPattern Formation and Solitons 0.685
## subcategoryPediatrics -8.973
## subcategoryPerformance 0.867
## subcategoryPharmacology and Therapeutics -6.060
## subcategoryPharmacology and Toxicology -13.895
## subcategoryPhysics and Society -2.094
## subcategoryPhysics Education -7.175
## subcategoryPhysiology -15.917
## subcategoryPlant Biology -16.073
## subcategoryPlasma Physics 2.133
## subcategoryPopular Physics -1.538
## subcategoryPopulations and Evolution -6.004
## subcategoryPortfolio Management -0.744
## subcategoryPricing of Securities 1.933
## subcategoryPrimary Care Research -3.946
## subcategoryProbability 0.880
## subcategoryProgramming Languages 2.412
## subcategoryPsychiatry and Clinical Psychology -14.599
## subcategoryPublic and Global Health -16.114
## subcategoryQuantitative Methods -6.782
## subcategoryQuantum Algebra 0.128
## subcategoryQuantum Gases 1.819
## subcategoryQuantum Physics 1.347
## subcategoryRadiology and Imaging -7.776
## subcategoryRehabilitation Medicine and Physical Therapy -8.635
## subcategoryRepresentation Theory -1.415
## subcategoryRespiratory Medicine -8.398
## subcategoryRheumatology -8.919
## subcategoryRings and Algebras -2.851
## subcategoryRisk Management -0.315
## subcategoryRobotics 1.087
## subcategoryScientific Communication and Education -15.053
## subcategorySexual and Reproductive Health -8.330
## subcategorySignal Processing -1.714
## subcategorySocial and Information Networks -3.654
## subcategorySoft Condensed Matter -1.611
## subcategorySoftware Engineering -0.231
## subcategorySolar and Stellar Astrophysics -6.299
## subcategorySound -1.083
## subcategorySpace Physics -1.663
## subcategorySpectral Theory 0.425
## subcategorySports Medicine -0.963
## subcategoryStatistical Finance 0.138
## subcategoryStatistical Mechanics 2.957
## subcategoryStatistics Theory -2.216
## subcategoryStrongly Correlated Electrons 1.322
## subcategorySubcellular Processes -2.781
## subcategorySuperconductivity -0.075
## subcategorySurgery -2.322
## subcategorySymbolic Computation 1.042
## subcategorySymplectic Geometry 0.624
## subcategorySynthetic Biology -9.275
## subcategorySystems and Control 1.211
## subcategorySystems Biology -10.468
## subcategoryTheoretical Economics 1.957
## subcategoryTissues and Organs -7.250
## subcategoryTrading and Market Microstructure 0.810
## subcategoryZoology -7.759
## Pr(>|t|)
## (Intercept) < 2e-16
## month < 2e-16
## covidTRUE 0.014213
## covidpaperTRUE 0.000160
## subcategoryAdaptation and Self-Organizing Systems 0.299895
## subcategoryAddiction Medicine 7.36e-05
## subcategoryAlgebraic Geometry 0.361774
## subcategoryAlgebraic Topology 0.493010
## subcategoryAllergy and Immunology 4.49e-16
## subcategoryAnalysis of PDEs 0.112980
## subcategoryAnimal Behavior and Cognition < 2e-16
## subcategoryApplications 5.99e-10
## subcategoryApplied Physics 0.080352
## subcategoryArtificial Intelligence 0.186779
## subcategoryAstrophysics of Galaxies < 2e-16
## subcategoryAtmospheric and Oceanic Physics 0.607793
## subcategoryAtomic and Molecular Clusters 0.247739
## subcategoryAtomic Physics 0.146662
## subcategoryAudio and Speech Processing 0.140088
## subcategoryBiochemistry < 2e-16
## subcategoryBioengineering < 2e-16
## subcategoryBioinformatics < 2e-16
## subcategoryBiological Physics 0.000453
## subcategoryBiomolecules 3.36e-06
## subcategoryBiophysics < 2e-16
## subcategoryCancer Biology < 2e-16
## subcategoryCardiovascular Medicine 6.92e-08
## subcategoryCategory Theory 0.716500
## subcategoryCell Behavior 1.71e-07
## subcategoryCell Biology < 2e-16
## subcategoryChaotic Dynamics 0.309019
## subcategoryChemical Physics 0.364504
## subcategoryClassical Analysis and ODEs 0.736946
## subcategoryClassical Physics 0.186375
## subcategoryClinical Trials 6.54e-16
## subcategoryCombinatorics 0.017946
## subcategoryCommutative Algebra 0.072424
## subcategoryComplex Variables 0.081905
## subcategoryComputation 0.394535
## subcategoryComputation and Language 5.55e-07
## subcategoryComputational Complexity 0.007513
## subcategoryComputational Engineering, Finance, and Science 0.425918
## subcategoryComputational Finance 0.138621
## subcategoryComputational Geometry 0.166661
## subcategoryComputational Physics 0.033490
## subcategoryComputer Science and Game Theory 0.994376
## subcategoryComputer Vision and Pattern Recognition 0.012536
## subcategoryComputers and Society 3.04e-11
## subcategoryCosmology and Nongalactic Astrophysics 0.003432
## subcategoryCryptography and Security 0.467008
## subcategoryData Analysis, Statistics and Probability 0.707713
## subcategoryData Structures and Algorithms 0.084177
## subcategoryDatabases 0.053402
## subcategoryDermatology 0.043304
## subcategoryDevelopmental Biology < 2e-16
## subcategoryDifferential Geometry 0.226828
## subcategoryDigital Libraries 1.06e-05
## subcategoryDiscrete Mathematics 0.291344
## subcategoryDisordered Systems and Neural Networks 0.428999
## subcategoryDistributed, Parallel, and Cluster Computing 0.558888
## subcategoryDynamical Systems 0.298109
## subcategoryEarth and Planetary Astrophysics 4.32e-08
## subcategoryEcology < 2e-16
## subcategoryEconometrics 0.072910
## subcategoryEconomics 0.777764
## subcategoryEmergency Medicine 0.000275
## subcategoryEmerging Technologies 0.192605
## subcategoryEndocrinology (including Diabetes Mellitus and Metabolic Disease) 7.33e-13
## subcategoryEpidemiology < 2e-16
## subcategoryEvolutionary Biology < 2e-16
## subcategoryExactly Solvable and Integrable Systems 0.858662
## subcategoryFluid Dynamics 0.021512
## subcategoryFormal Languages and Automata Theory 0.884055
## subcategoryFunctional Analysis 0.617738
## subcategoryGastroenterology 2.34e-15
## subcategoryGeneral Economics 0.464499
## subcategoryGeneral Finance 0.512102
## subcategoryGeneral Literature 0.568790
## subcategoryGeneral Mathematics 0.501536
## subcategoryGeneral Physics 0.111175
## subcategoryGeneral Relativity and Quantum Cosmology 0.327303
## subcategoryGeneral Topology 0.396508
## subcategoryGenetic and Genomic Medicine < 2e-16
## subcategoryGenetics < 2e-16
## subcategoryGenomics < 2e-16
## subcategoryGeometric Topology 0.060451
## subcategoryGeophysics 0.539405
## subcategoryGeriatric Medicine 0.571089
## subcategoryGraphics 0.650666
## subcategoryGroup Theory 0.700705
## subcategoryHardware Architecture 0.151066
## subcategoryHealth Economics 0.382394
## subcategoryHealth Informatics 5.94e-13
## subcategoryHealth Policy 6.91e-09
## subcategoryHealth Systems and Quality Improvement 1.24e-12
## subcategoryHematology 0.021633
## subcategoryHigh Energy Astrophysical Phenomena 0.000240
## subcategoryHigh Energy Physics - Experiment 0.041241
## subcategoryHigh Energy Physics - Lattice 4.92e-05
## subcategoryHigh Energy Physics - Phenomenology 0.970440
## subcategoryHigh Energy Physics - Theory 0.000672
## subcategoryHistory and Overview 0.346882
## subcategoryHistory and Philosophy of Physics 0.112549
## subcategoryHIV/AIDS 4.37e-11
## subcategoryHuman-Computer Interaction 6.69e-11
## subcategoryImage and Video Processing 0.004633
## subcategoryImmunology < 2e-16
## subcategoryInfectious Diseases (except HIV/AIDS) < 2e-16
## subcategoryInformation Retrieval 3.16e-05
## subcategoryInformation Theory 0.058676
## subcategoryInstrumentation and Detectors 0.685982
## subcategoryInstrumentation and Methods for Astrophysics 0.001103
## subcategoryIntensive Care and Critical Care Medicine 3.25e-09
## subcategoryK-Theory and Homology 0.015611
## subcategoryLogic 0.000711
## subcategoryLogic in Computer Science 0.042274
## subcategoryMachine Learning 0.729747
## subcategoryMaterials Science 0.023644
## subcategoryMathematical Finance 0.477257
## subcategoryMathematical Physics 0.000316
## subcategoryMathematical Software 0.060726
## subcategoryMedical Education 0.254456
## subcategoryMedical Physics 5.02e-05
## subcategoryMesoscale and Nanoscale Physics 0.627104
## subcategoryMethodology 2.82e-05
## subcategoryMetric Geometry 0.082948
## subcategoryMicrobiology < 2e-16
## subcategoryMolecular Biology < 2e-16
## subcategoryMolecular Networks 3.58e-05
## subcategoryMultiagent Systems 0.874831
## subcategoryMultimedia 0.003271
## subcategoryNephrology 3.11e-07
## subcategoryNetworking and Internet Architecture 0.562673
## subcategoryNeural and Evolutionary Computing 0.303995
## subcategoryNeurology < 2e-16
## subcategoryNeurons and Cognition 1.26e-07
## subcategoryNeuroscience < 2e-16
## subcategoryNuclear Experiment 0.040960
## subcategoryNuclear Theory 0.694268
## subcategoryNumber Theory 0.123343
## subcategoryNumerical Analysis 0.727963
## subcategoryNutrition 2.33e-07
## subcategoryObstetrics and Gynecology 3.05e-12
## subcategoryOccupational and Environmental Health 1.06e-15
## subcategoryOncology < 2e-16
## subcategoryOperating Systems 0.242595
## subcategoryOperator Algebras 0.061797
## subcategoryOphthalmology 1.14e-07
## subcategoryOptics 0.900948
## subcategoryOptimization and Control 0.807180
## subcategoryOther Computer Science 0.423544
## subcategoryOther Condensed Matter 0.168807
## subcategoryOther Quantitative Biology 0.047058
## subcategoryOther Statistics 0.015975
## subcategoryOtolaryngology 0.201651
## subcategoryPaleontology 0.579127
## subcategoryPathology < 2e-16
## subcategoryPattern Formation and Solitons 0.493502
## subcategoryPediatrics < 2e-16
## subcategoryPerformance 0.385805
## subcategoryPharmacology and Therapeutics 1.52e-09
## subcategoryPharmacology and Toxicology < 2e-16
## subcategoryPhysics and Society 0.036342
## subcategoryPhysics Education 8.94e-13
## subcategoryPhysiology < 2e-16
## subcategoryPlant Biology < 2e-16
## subcategoryPlasma Physics 0.032998
## subcategoryPopular Physics 0.124143
## subcategoryPopulations and Evolution 2.14e-09
## subcategoryPortfolio Management 0.456889
## subcategoryPricing of Securities 0.053336
## subcategoryPrimary Care Research 8.12e-05
## subcategoryProbability 0.378823
## subcategoryProgramming Languages 0.015930
## subcategoryPsychiatry and Clinical Psychology < 2e-16
## subcategoryPublic and Global Health < 2e-16
## subcategoryQuantitative Methods 1.40e-11
## subcategoryQuantum Algebra 0.897886
## subcategoryQuantum Gases 0.068931
## subcategoryQuantum Physics 0.178111
## subcategoryRadiology and Imaging 9.95e-15
## subcategoryRehabilitation Medicine and Physical Therapy < 2e-16
## subcategoryRepresentation Theory 0.157190
## subcategoryRespiratory Medicine < 2e-16
## subcategoryRheumatology < 2e-16
## subcategoryRings and Algebras 0.004392
## subcategoryRisk Management 0.752963
## subcategoryRobotics 0.277191
## subcategoryScientific Communication and Education < 2e-16
## subcategorySexual and Reproductive Health < 2e-16
## subcategorySignal Processing 0.086590
## subcategorySocial and Information Networks 0.000262
## subcategorySoft Condensed Matter 0.107383
## subcategorySoftware Engineering 0.817538
## subcategorySolar and Stellar Astrophysics 3.39e-10
## subcategorySound 0.278846
## subcategorySpace Physics 0.096390
## subcategorySpectral Theory 0.670797
## subcategorySports Medicine 0.335706
## subcategoryStatistical Finance 0.889995
## subcategoryStatistical Mechanics 0.003133
## subcategoryStatistics Theory 0.026785
## subcategoryStrongly Correlated Electrons 0.186173
## subcategorySubcellular Processes 0.005453
## subcategorySuperconductivity 0.940437
## subcategorySurgery 0.020302
## subcategorySymbolic Computation 0.297619
## subcategorySymplectic Geometry 0.532848
## subcategorySynthetic Biology < 2e-16
## subcategorySystems and Control 0.225895
## subcategorySystems Biology < 2e-16
## subcategoryTheoretical Economics 0.050490
## subcategoryTissues and Organs 5.19e-13
## subcategoryTrading and Market Microstructure 0.418246
## subcategoryZoology 1.14e-14
##
## (Intercept) ***
## month ***
## covidTRUE *
## covidpaperTRUE ***
## subcategoryAdaptation and Self-Organizing Systems
## subcategoryAddiction Medicine ***
## subcategoryAlgebraic Geometry
## subcategoryAlgebraic Topology
## subcategoryAllergy and Immunology ***
## subcategoryAnalysis of PDEs
## subcategoryAnimal Behavior and Cognition ***
## subcategoryApplications ***
## subcategoryApplied Physics .
## subcategoryArtificial Intelligence
## subcategoryAstrophysics of Galaxies ***
## subcategoryAtmospheric and Oceanic Physics
## subcategoryAtomic and Molecular Clusters
## subcategoryAtomic Physics
## subcategoryAudio and Speech Processing
## subcategoryBiochemistry ***
## subcategoryBioengineering ***
## subcategoryBioinformatics ***
## subcategoryBiological Physics ***
## subcategoryBiomolecules ***
## subcategoryBiophysics ***
## subcategoryCancer Biology ***
## subcategoryCardiovascular Medicine ***
## subcategoryCategory Theory
## subcategoryCell Behavior ***
## subcategoryCell Biology ***
## subcategoryChaotic Dynamics
## subcategoryChemical Physics
## subcategoryClassical Analysis and ODEs
## subcategoryClassical Physics
## subcategoryClinical Trials ***
## subcategoryCombinatorics *
## subcategoryCommutative Algebra .
## subcategoryComplex Variables .
## subcategoryComputation
## subcategoryComputation and Language ***
## subcategoryComputational Complexity **
## subcategoryComputational Engineering, Finance, and Science
## subcategoryComputational Finance
## subcategoryComputational Geometry
## subcategoryComputational Physics *
## subcategoryComputer Science and Game Theory
## subcategoryComputer Vision and Pattern Recognition *
## subcategoryComputers and Society ***
## subcategoryCosmology and Nongalactic Astrophysics **
## subcategoryCryptography and Security
## subcategoryData Analysis, Statistics and Probability
## subcategoryData Structures and Algorithms .
## subcategoryDatabases .
## subcategoryDermatology *
## subcategoryDevelopmental Biology ***
## subcategoryDifferential Geometry
## subcategoryDigital Libraries ***
## subcategoryDiscrete Mathematics
## subcategoryDisordered Systems and Neural Networks
## subcategoryDistributed, Parallel, and Cluster Computing
## subcategoryDynamical Systems
## subcategoryEarth and Planetary Astrophysics ***
## subcategoryEcology ***
## subcategoryEconometrics .
## subcategoryEconomics
## subcategoryEmergency Medicine ***
## subcategoryEmerging Technologies
## subcategoryEndocrinology (including Diabetes Mellitus and Metabolic Disease) ***
## subcategoryEpidemiology ***
## subcategoryEvolutionary Biology ***
## subcategoryExactly Solvable and Integrable Systems
## subcategoryFluid Dynamics *
## subcategoryFormal Languages and Automata Theory
## subcategoryFunctional Analysis
## subcategoryGastroenterology ***
## subcategoryGeneral Economics
## subcategoryGeneral Finance
## subcategoryGeneral Literature
## subcategoryGeneral Mathematics
## subcategoryGeneral Physics
## subcategoryGeneral Relativity and Quantum Cosmology
## subcategoryGeneral Topology
## subcategoryGenetic and Genomic Medicine ***
## subcategoryGenetics ***
## subcategoryGenomics ***
## subcategoryGeometric Topology .
## subcategoryGeophysics
## subcategoryGeriatric Medicine
## subcategoryGraphics
## subcategoryGroup Theory
## subcategoryHardware Architecture
## subcategoryHealth Economics
## subcategoryHealth Informatics ***
## subcategoryHealth Policy ***
## subcategoryHealth Systems and Quality Improvement ***
## subcategoryHematology *
## subcategoryHigh Energy Astrophysical Phenomena ***
## subcategoryHigh Energy Physics - Experiment *
## subcategoryHigh Energy Physics - Lattice ***
## subcategoryHigh Energy Physics - Phenomenology
## subcategoryHigh Energy Physics - Theory ***
## subcategoryHistory and Overview
## subcategoryHistory and Philosophy of Physics
## subcategoryHIV/AIDS ***
## subcategoryHuman-Computer Interaction ***
## subcategoryImage and Video Processing **
## subcategoryImmunology ***
## subcategoryInfectious Diseases (except HIV/AIDS) ***
## subcategoryInformation Retrieval ***
## subcategoryInformation Theory .
## subcategoryInstrumentation and Detectors
## subcategoryInstrumentation and Methods for Astrophysics **
## subcategoryIntensive Care and Critical Care Medicine ***
## subcategoryK-Theory and Homology *
## subcategoryLogic ***
## subcategoryLogic in Computer Science *
## subcategoryMachine Learning
## subcategoryMaterials Science *
## subcategoryMathematical Finance
## subcategoryMathematical Physics ***
## subcategoryMathematical Software .
## subcategoryMedical Education
## subcategoryMedical Physics ***
## subcategoryMesoscale and Nanoscale Physics
## subcategoryMethodology ***
## subcategoryMetric Geometry .
## subcategoryMicrobiology ***
## subcategoryMolecular Biology ***
## subcategoryMolecular Networks ***
## subcategoryMultiagent Systems
## subcategoryMultimedia **
## subcategoryNephrology ***
## subcategoryNetworking and Internet Architecture
## subcategoryNeural and Evolutionary Computing
## subcategoryNeurology ***
## subcategoryNeurons and Cognition ***
## subcategoryNeuroscience ***
## subcategoryNuclear Experiment *
## subcategoryNuclear Theory
## subcategoryNumber Theory
## subcategoryNumerical Analysis
## subcategoryNutrition ***
## subcategoryObstetrics and Gynecology ***
## subcategoryOccupational and Environmental Health ***
## subcategoryOncology ***
## subcategoryOperating Systems
## subcategoryOperator Algebras .
## subcategoryOphthalmology ***
## subcategoryOptics
## subcategoryOptimization and Control
## subcategoryOther Computer Science
## subcategoryOther Condensed Matter
## subcategoryOther Quantitative Biology *
## subcategoryOther Statistics *
## subcategoryOtolaryngology
## subcategoryPaleontology
## subcategoryPathology ***
## subcategoryPattern Formation and Solitons
## subcategoryPediatrics ***
## subcategoryPerformance
## subcategoryPharmacology and Therapeutics ***
## subcategoryPharmacology and Toxicology ***
## subcategoryPhysics and Society *
## subcategoryPhysics Education ***
## subcategoryPhysiology ***
## subcategoryPlant Biology ***
## subcategoryPlasma Physics *
## subcategoryPopular Physics
## subcategoryPopulations and Evolution ***
## subcategoryPortfolio Management
## subcategoryPricing of Securities .
## subcategoryPrimary Care Research ***
## subcategoryProbability
## subcategoryProgramming Languages *
## subcategoryPsychiatry and Clinical Psychology ***
## subcategoryPublic and Global Health ***
## subcategoryQuantitative Methods ***
## subcategoryQuantum Algebra
## subcategoryQuantum Gases .
## subcategoryQuantum Physics
## subcategoryRadiology and Imaging ***
## subcategoryRehabilitation Medicine and Physical Therapy ***
## subcategoryRepresentation Theory
## subcategoryRespiratory Medicine ***
## subcategoryRheumatology ***
## subcategoryRings and Algebras **
## subcategoryRisk Management
## subcategoryRobotics
## subcategoryScientific Communication and Education ***
## subcategorySexual and Reproductive Health ***
## subcategorySignal Processing .
## subcategorySocial and Information Networks ***
## subcategorySoft Condensed Matter
## subcategorySoftware Engineering
## subcategorySolar and Stellar Astrophysics ***
## subcategorySound
## subcategorySpace Physics .
## subcategorySpectral Theory
## subcategorySports Medicine
## subcategoryStatistical Finance
## subcategoryStatistical Mechanics **
## subcategoryStatistics Theory *
## subcategoryStrongly Correlated Electrons
## subcategorySubcellular Processes **
## subcategorySuperconductivity
## subcategorySurgery *
## subcategorySymbolic Computation
## subcategorySymplectic Geometry
## subcategorySynthetic Biology ***
## subcategorySystems and Control
## subcategorySystems Biology ***
## subcategoryTheoretical Economics .
## subcategoryTissues and Organs ***
## subcategoryTrading and Market Microstructure
## subcategoryZoology ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4939 on 3258 degrees of freedom
## Multiple R-squared: 0.9228, Adjusted R-squared: 0.9177
## F-statistic: 182 on 214 and 3258 DF, p-value: < 2.2e-16
El intercept está mucho mejor (0.85), y covid y covidpaper siguen saliendo positivos.
Vamos directamente con las subcategorías a partir de ahora.
fit_lmer <- lmer(
r_male ~ month + covid + covidpaper + (1 | category/subcategory),
df.agg, weights=total)
Ojo a esto:
model_performance(fit_lmer)
## `geom_smooth()` using formula 'y ~ x'
## pseudo-R2 = 0.7902072
Nice! Y los residuales:
model_assumptions(fit_lmer)
## `geom_smooth()` using formula 'y ~ x'
Pues siguen desviándose de la normal en las colas. Esto realmente es esperable, porque estamos con una proporción.
summary(fit_lmer)
## Linear mixed model fit by REML ['lmerMod']
## Formula: r_male ~ month + covid + covidpaper + (1 | category/subcategory)
## Data: df.agg
## Weights: total
##
## REML criterion at convergence: -13318.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.4942 -0.6234 0.0511 0.6869 5.7916
##
## Random effects:
## Groups Name Variance Std.Dev.
## subcategory:category (Intercept) 0.001467 0.0383
## category (Intercept) 0.006905 0.0831
## Residual 0.245707 0.4957
## Number of obs: 3473, groups: subcategory:category, 219; category, 8
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 8.072e-01 2.967e-02 27.209
## month -5.309e-04 3.974e-05 -13.359
## covidTRUE 2.858e-03 1.142e-03 2.502
## covidpaperTRUE 1.426e-02 3.436e-03 4.149
##
## Correlation of Fixed Effects:
## (Intr) month covdTRUE
## month -0.029
## covidTRUE 0.010 -0.621
## covdpprTRUE -0.006 0.004 -0.117
Intecept de 0.80, que está muy bien. Variables covid y covidpaper positivas (spoiler: salen siempre positivas). Lo bueno del modelo de efectos mixtos es que le cambias subcategorías por categoría y, aunque sale peor, como el modelo lineal, el intercept es estable, sale lo mismo.
Dado que la variable respuesta va de 0 a 1 de forma continua, lo suyo es un modelo binomial fraccional (binomial más los pesos de los counts).
Primero lo primero:
fit_glm <- glm(
r_male ~ month + covid + covidpaper + subcategory,
df.agg, family=binomial, weights=total)
Que nos da:
model_performance(fit_glm)
## `geom_smooth()` using formula 'y ~ x'
## pseudo-R2 = 0.8021809
Muy bien, similar a lo anterior, pero ahora:
model_assumptions(fit_glm)
## `geom_smooth()` using formula 'y ~ x'
Espectaculares residuales. No habéis visto unos residuales así ni en los ejercicios de clase. Finalmente, el chorizo:
summary(fit_glm)
##
## Call:
## glm(formula = r_male ~ month + covid + covidpaper + subcategory,
## family = binomial, data = df.agg, weights = total)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.4290 -0.7889 0.0597 0.8886 6.2448
##
## Coefficients:
## Estimate
## (Intercept) 1.7906290
## month -0.0035878
## covidTRUE 0.0201486
## covidpaperTRUE 0.0686645
## subcategoryAdaptation and Self-Organizing Systems -0.1210853
## subcategoryAddiction Medicine -1.2245290
## subcategoryAlgebraic Geometry 0.0860267
## subcategoryAlgebraic Topology 0.0741083
## subcategoryAllergy and Immunology -1.3312728
## subcategoryAnalysis of PDEs -0.1331888
## subcategoryAnimal Behavior and Cognition -1.0295705
## subcategoryApplications -0.4889835
## subcategoryApplied Physics -0.1469708
## subcategoryArtificial Intelligence -0.1099846
## subcategoryAstrophysics of Galaxies -0.5812649
## subcategoryAtmospheric and Oceanic Physics -0.0600170
## subcategoryAtomic and Molecular Clusters -0.1662142
## subcategoryAtomic Physics 0.1441790
## subcategoryAudio and Speech Processing -0.1360033
## subcategoryBiochemistry -0.9485172
## subcategoryBioengineering -0.7951614
## subcategoryBioinformatics -0.6942248
## subcategoryBiological Physics -0.3071894
## subcategoryBiomolecules -0.4995666
## subcategoryBiophysics -0.6512642
## subcategoryCancer Biology -1.1587973
## subcategoryCardiovascular Medicine -0.6514228
## subcategoryCategory Theory 0.0446107
## subcategoryCell Behavior -0.6345724
## subcategoryCell Biology -1.1781338
## subcategoryChaotic Dynamics 0.1224820
## subcategoryChemical Physics -0.0809671
## subcategoryClassical Analysis and ODEs -0.0324691
## subcategoryClassical Physics 0.1702294
## subcategoryClinical Trials -1.3085907
## subcategoryCombinatorics -0.1946686
## subcategoryCommutative Algebra -0.1879465
## subcategoryComplex Variables 0.1990709
## subcategoryComputation 0.0923011
## subcategoryComputation and Language -0.3787754
## subcategoryComputational Complexity 0.3197098
## subcategoryComputational Engineering, Finance, and Science 0.0930251
## subcategoryComputational Finance 0.3256898
## subcategoryComputational Geometry 0.1618636
## subcategoryComputational Physics 0.2057750
## subcategoryComputer Science and Game Theory -0.0006528
## subcategoryComputer Vision and Pattern Recognition -0.1962711
## subcategoryComputers and Society -0.5180530
## subcategoryCosmology and Nongalactic Astrophysics -0.2335422
## subcategoryCryptography and Security -0.0639659
## subcategoryData Analysis, Statistics and Probability 0.0407120
## subcategoryData Structures and Algorithms 0.1676698
## subcategoryDatabases -0.1828150
## subcategoryDermatology -0.9000102
## subcategoryDevelopmental Biology -1.2718727
## subcategoryDifferential Geometry 0.1180697
## subcategoryDigital Libraries -0.4591017
## subcategoryDiscrete Mathematics 0.1118695
## subcategoryDisordered Systems and Neural Networks 0.0813752
## subcategoryDistributed, Parallel, and Cluster Computing 0.0527612
## subcategoryDynamical Systems -0.0926232
## subcategoryEarth and Planetary Astrophysics -0.4155257
## subcategoryEcology -0.9420202
## subcategoryEconometrics 0.2666873
## subcategoryEconomics -0.0404329
## subcategoryEmergency Medicine -0.7892360
## subcategoryEmerging Technologies 0.1546881
## subcategoryEndocrinology (including Diabetes Mellitus and Metabolic Disease) -1.2240066
## subcategoryEpidemiology -1.0550866
## subcategoryEvolutionary Biology -0.9117578
## subcategoryExactly Solvable and Integrable Systems -0.0222482
## subcategoryFluid Dynamics 0.2298854
## subcategoryFormal Languages and Automata Theory 0.0178850
## subcategoryFunctional Analysis 0.0484504
## subcategoryGastroenterology -1.0872730
## subcategoryGeneral Economics -0.1056557
## subcategoryGeneral Finance 0.1260228
## subcategoryGeneral Literature 0.3608829
## subcategoryGeneral Mathematics 0.1857903
## subcategoryGeneral Physics 0.2789825
## subcategoryGeneral Relativity and Quantum Cosmology 0.0881830
## subcategoryGeneral Topology 0.1349127
## subcategoryGenetic and Genomic Medicine -1.3576512
## subcategoryGenetics -1.1603148
## subcategoryGenomics -1.0088927
## subcategoryGeometric Topology -0.1797397
## subcategoryGeophysics -0.0672101
## subcategoryGeriatric Medicine -0.2695927
## subcategoryGraphics 0.0505288
## subcategoryGroup Theory 0.0396576
## subcategoryHardware Architecture 0.1891817
## subcategoryHealth Economics -0.2853155
## subcategoryHealth Informatics -0.8067880
## subcategoryHealth Policy -1.0002238
## subcategoryHealth Systems and Quality Improvement -1.1276784
## subcategoryHematology -0.7994511
## subcategoryHigh Energy Astrophysical Phenomena -0.2882461
## subcategoryHigh Energy Physics - Experiment -0.1732588
## subcategoryHigh Energy Physics - Lattice 0.4866500
## subcategoryHigh Energy Physics - Phenomenology -0.0028699
## subcategoryHigh Energy Physics - Theory 0.3312903
## subcategoryHistory and Overview -0.1694207
## subcategoryHistory and Philosophy of Physics 0.3050251
## subcategoryHIV/AIDS -1.2938274
## subcategoryHuman-Computer Interaction -0.5170804
## subcategoryImage and Video Processing -0.2319061
## subcategoryImmunology -1.2549246
## subcategoryInfectious Diseases (except HIV/AIDS) -1.1548675
## subcategoryInformation Retrieval -0.3465199
## subcategoryInformation Theory -0.1523042
## subcategoryInstrumentation and Detectors -0.0359720
## subcategoryInstrumentation and Methods for Astrophysics -0.2610586
## subcategoryIntensive Care and Critical Care Medicine -0.7204437
## subcategoryK-Theory and Homology 0.4058772
## subcategoryLogic 0.4312608
## subcategoryLogic in Computer Science 0.2180962
## subcategoryMachine Learning -0.0305112
## subcategoryMaterials Science -0.1806757
## subcategoryMathematical Finance -0.1065532
## subcategoryMathematical Physics 0.3523437
## subcategoryMathematical Software 0.3394081
## subcategoryMedical Education -0.5388001
## subcategoryMedical Physics -0.3677675
## subcategoryMesoscale and Nanoscale Physics 0.0423900
## subcategoryMethodology -0.3417740
## subcategoryMetric Geometry 0.2123573
## subcategoryMicrobiology -1.1879277
## subcategoryMolecular Biology -1.1170126
## subcategoryMolecular Networks -0.4856762
## subcategoryMultiagent Systems 0.0149705
## subcategoryMultimedia -0.2943841
## subcategoryNephrology -1.2553441
## subcategoryNetworking and Internet Architecture -0.0515179
## subcategoryNeural and Evolutionary Computing 0.0984017
## subcategoryNeurology -1.0304242
## subcategoryNeurons and Cognition -0.4540945
## subcategoryNeuroscience -1.0074889
## subcategoryNuclear Experiment -0.1885058
## subcategoryNuclear Theory -0.0357352
## subcategoryNumber Theory 0.1502925
## subcategoryNumerical Analysis -0.0314609
## subcategoryNutrition -1.4512707
## subcategoryObstetrics and Gynecology -1.9751474
## subcategoryOccupational and Environmental Health -1.1795888
## subcategoryOncology -1.1736696
## subcategoryOperating Systems 0.3736746
## subcategoryOperator Algebras 0.2367342
## subcategoryOphthalmology -1.1354651
## subcategoryOptics 0.0106452
## subcategoryOptimization and Control 0.0207221
## subcategoryOther Computer Science -0.1533028
## subcategoryOther Condensed Matter 0.1711205
## subcategoryOther Quantitative Biology -0.6030829
## subcategoryOther Statistics -0.4762757
## subcategoryOtolaryngology -0.4645108
## subcategoryPaleontology -0.3033345
## subcategoryPathology -1.2170190
## subcategoryPattern Formation and Solitons 0.0849173
## subcategoryPediatrics -1.5103521
## subcategoryPerformance 0.1022853
## subcategoryPharmacology and Therapeutics -1.0513773
## subcategoryPharmacology and Toxicology -1.0883474
## subcategoryPhysics and Society -0.1825646
## subcategoryPhysics Education -0.8277015
## subcategoryPhysiology -1.1656361
## subcategoryPlant Biology -1.0717890
## subcategoryPlasma Physics 0.2345385
## subcategoryPopular Physics -0.3898514
## subcategoryPopulations and Evolution -0.5051949
## subcategoryPortfolio Management -0.2549847
## subcategoryPricing of Securities 0.8675079
## subcategoryPrimary Care Research -1.2140905
## subcategoryProbability 0.0805416
## subcategoryProgramming Languages 0.2861451
## subcategoryPsychiatry and Clinical Psychology -1.2779424
## subcategoryPublic and Global Health -1.2304036
## subcategoryQuantitative Methods -0.5504472
## subcategoryQuantum Algebra 0.0148351
## subcategoryQuantum Gases 0.1837496
## subcategoryQuantum Physics 0.1189275
## subcategoryRadiology and Imaging -0.9034832
## subcategoryRehabilitation Medicine and Physical Therapy -1.4216956
## subcategoryRepresentation Theory -0.1322485
## subcategoryRespiratory Medicine -0.9921918
## subcategoryRheumatology -1.4324740
## subcategoryRings and Algebras -0.2734746
## subcategoryRisk Management -0.0731020
## subcategoryRobotics 0.0965292
## subcategoryScientific Communication and Education -1.4287383
## subcategorySexual and Reproductive Health -2.0568828
## subcategorySignal Processing -0.1446697
## subcategorySocial and Information Networks -0.3003763
## subcategorySoft Condensed Matter -0.1392464
## subcategorySoftware Engineering -0.0220942
## subcategorySolar and Stellar Astrophysics -0.4648535
## subcategorySound -0.1016183
## subcategorySpace Physics -0.1777003
## subcategorySpectral Theory 0.0513052
## subcategorySports Medicine -0.4141740
## subcategoryStatistical Finance 0.0216992
## subcategoryStatistical Mechanics 0.2939068
## subcategoryStatistics Theory -0.1865298
## subcategoryStrongly Correlated Electrons 0.1195787
## subcategorySubcellular Processes -0.5010973
## subcategorySuperconductivity -0.0063040
## subcategorySurgery -0.7451258
## subcategorySymbolic Computation 0.1915519
## subcategorySymplectic Geometry 0.0808280
## subcategorySynthetic Biology -0.8409853
## subcategorySystems and Control 0.1048150
## subcategorySystems Biology -0.7781593
## subcategoryTheoretical Economics 0.4423263
## subcategoryTissues and Organs -0.7844892
## subcategoryTrading and Market Microstructure 0.2580317
## subcategoryZoology -0.9438615
## Std. Error
## (Intercept) 0.0604344
## month 0.0002091
## covidTRUE 0.0058238
## covidpaperTRUE 0.0154456
## subcategoryAdaptation and Self-Organizing Systems 0.0870684
## subcategoryAddiction Medicine 0.2456514
## subcategoryAlgebraic Geometry 0.0669799
## subcategoryAlgebraic Topology 0.0778336
## subcategoryAllergy and Immunology 0.1350824
## subcategoryAnalysis of PDEs 0.0638362
## subcategoryAnimal Behavior and Cognition 0.0740245
## subcategoryApplications 0.0658323
## subcategoryApplied Physics 0.0637525
## subcategoryArtificial Intelligence 0.0626257
## subcategoryAstrophysics of Galaxies 0.0613736
## subcategoryAtmospheric and Oceanic Physics 0.0850908
## subcategoryAtomic and Molecular Clusters 0.1068218
## subcategoryAtomic Physics 0.0697183
## subcategoryAudio and Speech Processing 0.0688973
## subcategoryBiochemistry 0.0640778
## subcategoryBioengineering 0.0670681
## subcategoryBioinformatics 0.0625130
## subcategoryBiological Physics 0.0689973
## subcategoryBiomolecules 0.0851478
## subcategoryBiophysics 0.0652723
## subcategoryCancer Biology 0.0627848
## subcategoryCardiovascular Medicine 0.0968292
## subcategoryCategory Theory 0.0902727
## subcategoryCell Behavior 0.0958935
## subcategoryCell Biology 0.0624824
## subcategoryChaotic Dynamics 0.0855352
## subcategoryChemical Physics 0.0666942
## subcategoryClassical Analysis and ODEs 0.0728951
## subcategoryClassical Physics 0.0906823
## subcategoryClinical Trials 0.1323829
## subcategoryCombinatorics 0.0636176
## subcategoryCommutative Algebra 0.0792118
## subcategoryComplex Variables 0.0799631
## subcategoryComputation 0.0783684
## subcategoryComputation and Language 0.0622270
## subcategoryComputational Complexity 0.0817536
## subcategoryComputational Engineering, Finance, and Science 0.0845282
## subcategoryComputational Finance 0.1622521
## subcategoryComputational Geometry 0.0832640
## subcategoryComputational Physics 0.0673851
## subcategoryComputer Science and Game Theory 0.0752105
## subcategoryComputer Vision and Pattern Recognition 0.0611526
## subcategoryComputers and Society 0.0655470
## subcategoryCosmology and Nongalactic Astrophysics 0.0625711
## subcategoryCryptography and Security 0.0644002
## subcategoryData Analysis, Statistics and Probability 0.0786875
## subcategoryData Structures and Algorithms 0.0676475
## subcategoryDatabases 0.0719993
## subcategoryDermatology 0.3410053
## subcategoryDevelopmental Biology 0.0647338
## subcategoryDifferential Geometry 0.0686771
## subcategoryDigital Libraries 0.0823095
## subcategoryDiscrete Mathematics 0.0753873
## subcategoryDisordered Systems and Neural Networks 0.0740946
## subcategoryDistributed, Parallel, and Cluster Computing 0.0659370
## subcategoryDynamical Systems 0.0667071
## subcategoryEarth and Planetary Astrophysics 0.0627023
## subcategoryEcology 0.0644408
## subcategoryEconometrics 0.1075249
## subcategoryEconomics 0.1026112
## subcategoryEmergency Medicine 0.1681004
## subcategoryEmerging Technologies 0.0851308
## subcategoryEndocrinology (including Diabetes Mellitus and Metabolic Disease) 0.1393856
## subcategoryEpidemiology 0.0635643
## subcategoryEvolutionary Biology 0.0640502
## subcategoryExactly Solvable and Integrable Systems 0.0953404
## subcategoryFluid Dynamics 0.0685440
## subcategoryFormal Languages and Automata Theory 0.0911591
## subcategoryFunctional Analysis 0.0696244
## subcategoryGastroenterology 0.1128672
## subcategoryGeneral Economics 0.1059564
## subcategoryGeneral Finance 0.1422390
## subcategoryGeneral Literature 0.4795446
## subcategoryGeneral Mathematics 0.2084903
## subcategoryGeneral Physics 0.1238798
## subcategoryGeneral Relativity and Quantum Cosmology 0.0636612
## subcategoryGeneral Topology 0.1149309
## subcategoryGenetic and Genomic Medicine 0.0736198
## subcategoryGenetics 0.0621692
## subcategoryGenomics 0.0618435
## subcategoryGeometric Topology 0.0727595
## subcategoryGeophysics 0.0806879
## subcategoryGeriatric Medicine 0.3749931
## subcategoryGraphics 0.0829769
## subcategoryGroup Theory 0.0740042
## subcategoryHardware Architecture 0.0931445
## subcategoryHealth Economics 0.2454498
## subcategoryHealth Informatics 0.0921585
## subcategoryHealth Policy 0.1376315
## subcategoryHealth Systems and Quality Improvement 0.1288631
## subcategoryHematology 0.2656213
## subcategoryHigh Energy Astrophysical Phenomena 0.0625525
## subcategoryHigh Energy Physics - Experiment 0.0650496
## subcategoryHigh Energy Physics - Lattice 0.0783358
## subcategoryHigh Energy Physics - Phenomenology 0.0624768
## subcategoryHigh Energy Physics - Theory 0.0636110
## subcategoryHistory and Overview 0.1321490
## subcategoryHistory and Philosophy of Physics 0.1392871
## subcategoryHIV/AIDS 0.1598703
## subcategoryHuman-Computer Interaction 0.0663657
## subcategoryImage and Video Processing 0.0642542
## subcategoryImmunology 0.0632010
## subcategoryInfectious Diseases (except HIV/AIDS) 0.0641364
## subcategoryInformation Retrieval 0.0668131
## subcategoryInformation Theory 0.0618090
## subcategoryInstrumentation and Detectors 0.0658822
## subcategoryInstrumentation and Methods for Astrophysics 0.0631789
## subcategoryIntensive Care and Critical Care Medicine 0.0983026
## subcategoryK-Theory and Homology 0.1183890
## subcategoryLogic 0.0859353
## subcategoryLogic in Computer Science 0.0742622
## subcategoryMachine Learning 0.0607625
## subcategoryMaterials Science 0.0617238
## subcategoryMathematical Finance 0.1100139
## subcategoryMathematical Physics 0.0633133
## subcategoryMathematical Software 0.1288980
## subcategoryMedical Education 0.3520911
## subcategoryMedical Physics 0.0721399
## subcategoryMesoscale and Nanoscale Physics 0.0621886
## subcategoryMethodology 0.0655571
## subcategoryMetric Geometry 0.0856199
## subcategoryMicrobiology 0.0616344
## subcategoryMolecular Biology 0.0638727
## subcategoryMolecular Networks 0.0916508
## subcategoryMultiagent Systems 0.0779018
## subcategoryMultimedia 0.0774268
## subcategoryNephrology 0.1957095
## subcategoryNetworking and Internet Architecture 0.0656203
## subcategoryNeural and Evolutionary Computing 0.0683376
## subcategoryNeurology 0.0798162
## subcategoryNeurons and Cognition 0.0697942
## subcategoryNeuroscience 0.0611459
## subcategoryNuclear Experiment 0.0704312
## subcategoryNuclear Theory 0.0671400
## subcategoryNumber Theory 0.0682814
## subcategoryNumerical Analysis 0.0635493
## subcategoryNutrition 0.2289396
## subcategoryObstetrics and Gynecology 0.2477171
## subcategoryOccupational and Environmental Health 0.1208671
## subcategoryOncology 0.0795482
## subcategoryOperating Systems 0.2341257
## subcategoryOperator Algebras 0.0886018
## subcategoryOphthalmology 0.1711520
## subcategoryOptics 0.0630789
## subcategoryOptimization and Control 0.0638022
## subcategoryOther Computer Science 0.1413685
## subcategoryOther Condensed Matter 0.0878662
## subcategoryOther Quantitative Biology 0.2294327
## subcategoryOther Statistics 0.1488055
## subcategoryOtolaryngology 0.2745816
## subcategoryPaleontology 0.4011302
## subcategoryPathology 0.0748266
## subcategoryPattern Formation and Solitons 0.0888257
## subcategoryPediatrics 0.1422693
## subcategoryPerformance 0.0869472
## subcategoryPharmacology and Therapeutics 0.1392692
## subcategoryPharmacology and Toxicology 0.0721092
## subcategoryPhysics and Society 0.0675365
## subcategoryPhysics Education 0.0941145
## subcategoryPhysiology 0.0696458
## subcategoryPlant Biology 0.0646476
## subcategoryPlasma Physics 0.0759909
## subcategoryPopular Physics 0.1883804
## subcategoryPopulations and Evolution 0.0698357
## subcategoryPortfolio Management 0.2505047
## subcategoryPricing of Securities 0.3335472
## subcategoryPrimary Care Research 0.2438405
## subcategoryProbability 0.0651610
## subcategoryProgramming Languages 0.0818814
## subcategoryPsychiatry and Clinical Psychology 0.0801574
## subcategoryPublic and Global Health 0.0721422
## subcategoryQuantitative Methods 0.0682245
## subcategoryQuantum Algebra 0.0815742
## subcategoryQuantum Gases 0.0700780
## subcategoryQuantum Physics 0.0619975
## subcategoryRadiology and Imaging 0.0963135
## subcategoryRehabilitation Medicine and Physical Therapy 0.1383516
## subcategoryRepresentation Theory 0.0705176
## subcategoryRespiratory Medicine 0.0985049
## subcategoryRheumatology 0.1346048
## subcategoryRings and Algebras 0.0743044
## subcategoryRisk Management 0.1647412
## subcategoryRobotics 0.0647527
## subcategoryScientific Communication and Education 0.0861757
## subcategorySexual and Reproductive Health 0.2180886
## subcategorySignal Processing 0.0638010
## subcategorySocial and Information Networks 0.0654391
## subcategorySoft Condensed Matter 0.0656951
## subcategorySoftware Engineering 0.0694222
## subcategorySolar and Stellar Astrophysics 0.0621695
## subcategorySound 0.0692876
## subcategorySpace Physics 0.0804890
## subcategorySpectral Theory 0.0868332
## subcategorySports Medicine 0.3307919
## subcategoryStatistical Finance 0.1323980
## subcategoryStatistical Mechanics 0.0664578
## subcategoryStatistics Theory 0.0648323
## subcategoryStrongly Correlated Electrons 0.0639437
## subcategorySubcellular Processes 0.1360181
## subcategorySuperconductivity 0.0666659
## subcategorySurgery 0.2439676
## subcategorySymbolic Computation 0.1322269
## subcategorySymplectic Geometry 0.0933172
## subcategorySynthetic Biology 0.0776925
## subcategorySystems and Control 0.0638189
## subcategorySystems Biology 0.0664443
## subcategoryTheoretical Economics 0.1673625
## subcategoryTissues and Organs 0.0889119
## subcategoryTrading and Market Microstructure 0.2412556
## subcategoryZoology 0.1003155
## z value
## (Intercept) 29.629
## month -17.162
## covidTRUE 3.460
## covidpaperTRUE 4.446
## subcategoryAdaptation and Self-Organizing Systems -1.391
## subcategoryAddiction Medicine -4.985
## subcategoryAlgebraic Geometry 1.284
## subcategoryAlgebraic Topology 0.952
## subcategoryAllergy and Immunology -9.855
## subcategoryAnalysis of PDEs -2.086
## subcategoryAnimal Behavior and Cognition -13.909
## subcategoryApplications -7.428
## subcategoryApplied Physics -2.305
## subcategoryArtificial Intelligence -1.756
## subcategoryAstrophysics of Galaxies -9.471
## subcategoryAtmospheric and Oceanic Physics -0.705
## subcategoryAtomic and Molecular Clusters -1.556
## subcategoryAtomic Physics 2.068
## subcategoryAudio and Speech Processing -1.974
## subcategoryBiochemistry -14.803
## subcategoryBioengineering -11.856
## subcategoryBioinformatics -11.105
## subcategoryBiological Physics -4.452
## subcategoryBiomolecules -5.867
## subcategoryBiophysics -9.978
## subcategoryCancer Biology -18.457
## subcategoryCardiovascular Medicine -6.728
## subcategoryCategory Theory 0.494
## subcategoryCell Behavior -6.617
## subcategoryCell Biology -18.855
## subcategoryChaotic Dynamics 1.432
## subcategoryChemical Physics -1.214
## subcategoryClassical Analysis and ODEs -0.445
## subcategoryClassical Physics 1.877
## subcategoryClinical Trials -9.885
## subcategoryCombinatorics -3.060
## subcategoryCommutative Algebra -2.373
## subcategoryComplex Variables 2.490
## subcategoryComputation 1.178
## subcategoryComputation and Language -6.087
## subcategoryComputational Complexity 3.911
## subcategoryComputational Engineering, Finance, and Science 1.101
## subcategoryComputational Finance 2.007
## subcategoryComputational Geometry 1.944
## subcategoryComputational Physics 3.054
## subcategoryComputer Science and Game Theory -0.009
## subcategoryComputer Vision and Pattern Recognition -3.210
## subcategoryComputers and Society -7.904
## subcategoryCosmology and Nongalactic Astrophysics -3.732
## subcategoryCryptography and Security -0.993
## subcategoryData Analysis, Statistics and Probability 0.517
## subcategoryData Structures and Algorithms 2.479
## subcategoryDatabases -2.539
## subcategoryDermatology -2.639
## subcategoryDevelopmental Biology -19.648
## subcategoryDifferential Geometry 1.719
## subcategoryDigital Libraries -5.578
## subcategoryDiscrete Mathematics 1.484
## subcategoryDisordered Systems and Neural Networks 1.098
## subcategoryDistributed, Parallel, and Cluster Computing 0.800
## subcategoryDynamical Systems -1.389
## subcategoryEarth and Planetary Astrophysics -6.627
## subcategoryEcology -14.618
## subcategoryEconometrics 2.480
## subcategoryEconomics -0.394
## subcategoryEmergency Medicine -4.695
## subcategoryEmerging Technologies 1.817
## subcategoryEndocrinology (including Diabetes Mellitus and Metabolic Disease) -8.781
## subcategoryEpidemiology -16.599
## subcategoryEvolutionary Biology -14.235
## subcategoryExactly Solvable and Integrable Systems -0.233
## subcategoryFluid Dynamics 3.354
## subcategoryFormal Languages and Automata Theory 0.196
## subcategoryFunctional Analysis 0.696
## subcategoryGastroenterology -9.633
## subcategoryGeneral Economics -0.997
## subcategoryGeneral Finance 0.886
## subcategoryGeneral Literature 0.753
## subcategoryGeneral Mathematics 0.891
## subcategoryGeneral Physics 2.252
## subcategoryGeneral Relativity and Quantum Cosmology 1.385
## subcategoryGeneral Topology 1.174
## subcategoryGenetic and Genomic Medicine -18.441
## subcategoryGenetics -18.664
## subcategoryGenomics -16.314
## subcategoryGeometric Topology -2.470
## subcategoryGeophysics -0.833
## subcategoryGeriatric Medicine -0.719
## subcategoryGraphics 0.609
## subcategoryGroup Theory 0.536
## subcategoryHardware Architecture 2.031
## subcategoryHealth Economics -1.162
## subcategoryHealth Informatics -8.754
## subcategoryHealth Policy -7.267
## subcategoryHealth Systems and Quality Improvement -8.751
## subcategoryHematology -3.010
## subcategoryHigh Energy Astrophysical Phenomena -4.608
## subcategoryHigh Energy Physics - Experiment -2.663
## subcategoryHigh Energy Physics - Lattice 6.212
## subcategoryHigh Energy Physics - Phenomenology -0.046
## subcategoryHigh Energy Physics - Theory 5.208
## subcategoryHistory and Overview -1.282
## subcategoryHistory and Philosophy of Physics 2.190
## subcategoryHIV/AIDS -8.093
## subcategoryHuman-Computer Interaction -7.791
## subcategoryImage and Video Processing -3.609
## subcategoryImmunology -19.856
## subcategoryInfectious Diseases (except HIV/AIDS) -18.006
## subcategoryInformation Retrieval -5.186
## subcategoryInformation Theory -2.464
## subcategoryInstrumentation and Detectors -0.546
## subcategoryInstrumentation and Methods for Astrophysics -4.132
## subcategoryIntensive Care and Critical Care Medicine -7.329
## subcategoryK-Theory and Homology 3.428
## subcategoryLogic 5.018
## subcategoryLogic in Computer Science 2.937
## subcategoryMachine Learning -0.502
## subcategoryMaterials Science -2.927
## subcategoryMathematical Finance -0.969
## subcategoryMathematical Physics 5.565
## subcategoryMathematical Software 2.633
## subcategoryMedical Education -1.530
## subcategoryMedical Physics -5.098
## subcategoryMesoscale and Nanoscale Physics 0.682
## subcategoryMethodology -5.213
## subcategoryMetric Geometry 2.480
## subcategoryMicrobiology -19.274
## subcategoryMolecular Biology -17.488
## subcategoryMolecular Networks -5.299
## subcategoryMultiagent Systems 0.192
## subcategoryMultimedia -3.802
## subcategoryNephrology -6.414
## subcategoryNetworking and Internet Architecture -0.785
## subcategoryNeural and Evolutionary Computing 1.440
## subcategoryNeurology -12.910
## subcategoryNeurons and Cognition -6.506
## subcategoryNeuroscience -16.477
## subcategoryNuclear Experiment -2.676
## subcategoryNuclear Theory -0.532
## subcategoryNumber Theory 2.201
## subcategoryNumerical Analysis -0.495
## subcategoryNutrition -6.339
## subcategoryObstetrics and Gynecology -7.973
## subcategoryOccupational and Environmental Health -9.759
## subcategoryOncology -14.754
## subcategoryOperating Systems 1.596
## subcategoryOperator Algebras 2.672
## subcategoryOphthalmology -6.634
## subcategoryOptics 0.169
## subcategoryOptimization and Control 0.325
## subcategoryOther Computer Science -1.084
## subcategoryOther Condensed Matter 1.948
## subcategoryOther Quantitative Biology -2.629
## subcategoryOther Statistics -3.201
## subcategoryOtolaryngology -1.692
## subcategoryPaleontology -0.756
## subcategoryPathology -16.265
## subcategoryPattern Formation and Solitons 0.956
## subcategoryPediatrics -10.616
## subcategoryPerformance 1.176
## subcategoryPharmacology and Therapeutics -7.549
## subcategoryPharmacology and Toxicology -15.093
## subcategoryPhysics and Society -2.703
## subcategoryPhysics Education -8.795
## subcategoryPhysiology -16.737
## subcategoryPlant Biology -16.579
## subcategoryPlasma Physics 3.086
## subcategoryPopular Physics -2.069
## subcategoryPopulations and Evolution -7.234
## subcategoryPortfolio Management -1.018
## subcategoryPricing of Securities 2.601
## subcategoryPrimary Care Research -4.979
## subcategoryProbability 1.236
## subcategoryProgramming Languages 3.495
## subcategoryPsychiatry and Clinical Psychology -15.943
## subcategoryPublic and Global Health -17.055
## subcategoryQuantitative Methods -8.068
## subcategoryQuantum Algebra 0.182
## subcategoryQuantum Gases 2.622
## subcategoryQuantum Physics 1.918
## subcategoryRadiology and Imaging -9.381
## subcategoryRehabilitation Medicine and Physical Therapy -10.276
## subcategoryRepresentation Theory -1.875
## subcategoryRespiratory Medicine -10.073
## subcategoryRheumatology -10.642
## subcategoryRings and Algebras -3.680
## subcategoryRisk Management -0.444
## subcategoryRobotics 1.491
## subcategoryScientific Communication and Education -16.579
## subcategorySexual and Reproductive Health -9.431
## subcategorySignal Processing -2.268
## subcategorySocial and Information Networks -4.590
## subcategorySoft Condensed Matter -2.120
## subcategorySoftware Engineering -0.318
## subcategorySolar and Stellar Astrophysics -7.477
## subcategorySound -1.467
## subcategorySpace Physics -2.208
## subcategorySpectral Theory 0.591
## subcategorySports Medicine -1.252
## subcategoryStatistical Finance 0.164
## subcategoryStatistical Mechanics 4.422
## subcategoryStatistics Theory -2.877
## subcategoryStrongly Correlated Electrons 1.870
## subcategorySubcellular Processes -3.684
## subcategorySuperconductivity -0.095
## subcategorySurgery -3.054
## subcategorySymbolic Computation 1.449
## subcategorySymplectic Geometry 0.866
## subcategorySynthetic Biology -10.825
## subcategorySystems and Control 1.642
## subcategorySystems Biology -11.711
## subcategoryTheoretical Economics 2.643
## subcategoryTissues and Organs -8.823
## subcategoryTrading and Market Microstructure 1.070
## subcategoryZoology -9.409
## Pr(>|z|)
## (Intercept) < 2e-16
## month < 2e-16
## covidTRUE 0.000541
## covidpaperTRUE 8.77e-06
## subcategoryAdaptation and Self-Organizing Systems 0.164319
## subcategoryAddiction Medicine 6.20e-07
## subcategoryAlgebraic Geometry 0.199014
## subcategoryAlgebraic Topology 0.341027
## subcategoryAllergy and Immunology < 2e-16
## subcategoryAnalysis of PDEs 0.036941
## subcategoryAnimal Behavior and Cognition < 2e-16
## subcategoryApplications 1.10e-13
## subcategoryApplied Physics 0.021148
## subcategoryArtificial Intelligence 0.079050
## subcategoryAstrophysics of Galaxies < 2e-16
## subcategoryAtmospheric and Oceanic Physics 0.480606
## subcategoryAtomic and Molecular Clusters 0.119709
## subcategoryAtomic Physics 0.038638
## subcategoryAudio and Speech Processing 0.048382
## subcategoryBiochemistry < 2e-16
## subcategoryBioengineering < 2e-16
## subcategoryBioinformatics < 2e-16
## subcategoryBiological Physics 8.50e-06
## subcategoryBiomolecules 4.44e-09
## subcategoryBiophysics < 2e-16
## subcategoryCancer Biology < 2e-16
## subcategoryCardiovascular Medicine 1.73e-11
## subcategoryCategory Theory 0.621181
## subcategoryCell Behavior 3.65e-11
## subcategoryCell Biology < 2e-16
## subcategoryChaotic Dynamics 0.152159
## subcategoryChemical Physics 0.224746
## subcategoryClassical Analysis and ODEs 0.656015
## subcategoryClassical Physics 0.060490
## subcategoryClinical Trials < 2e-16
## subcategoryCombinatorics 0.002214
## subcategoryCommutative Algebra 0.017658
## subcategoryComplex Variables 0.012791
## subcategoryComputation 0.238883
## subcategoryComputation and Language 1.15e-09
## subcategoryComputational Complexity 9.20e-05
## subcategoryComputational Engineering, Finance, and Science 0.271105
## subcategoryComputational Finance 0.044717
## subcategoryComputational Geometry 0.051898
## subcategoryComputational Physics 0.002260
## subcategoryComputer Science and Game Theory 0.993074
## subcategoryComputer Vision and Pattern Recognition 0.001330
## subcategoryComputers and Society 2.71e-15
## subcategoryCosmology and Nongalactic Astrophysics 0.000190
## subcategoryCryptography and Security 0.320585
## subcategoryData Analysis, Statistics and Probability 0.604885
## subcategoryData Structures and Algorithms 0.013191
## subcategoryDatabases 0.011113
## subcategoryDermatology 0.008308
## subcategoryDevelopmental Biology < 2e-16
## subcategoryDifferential Geometry 0.085578
## subcategoryDigital Libraries 2.44e-08
## subcategoryDiscrete Mathematics 0.137827
## subcategoryDisordered Systems and Neural Networks 0.272090
## subcategoryDistributed, Parallel, and Cluster Computing 0.423609
## subcategoryDynamical Systems 0.164983
## subcategoryEarth and Planetary Astrophysics 3.43e-11
## subcategoryEcology < 2e-16
## subcategoryEconometrics 0.013129
## subcategoryEconomics 0.693552
## subcategoryEmergency Medicine 2.67e-06
## subcategoryEmerging Technologies 0.069207
## subcategoryEndocrinology (including Diabetes Mellitus and Metabolic Disease) < 2e-16
## subcategoryEpidemiology < 2e-16
## subcategoryEvolutionary Biology < 2e-16
## subcategoryExactly Solvable and Integrable Systems 0.815485
## subcategoryFluid Dynamics 0.000797
## subcategoryFormal Languages and Automata Theory 0.844457
## subcategoryFunctional Analysis 0.486503
## subcategoryGastroenterology < 2e-16
## subcategoryGeneral Economics 0.318686
## subcategoryGeneral Finance 0.375621
## subcategoryGeneral Literature 0.451718
## subcategoryGeneral Mathematics 0.372864
## subcategoryGeneral Physics 0.024320
## subcategoryGeneral Relativity and Quantum Cosmology 0.165994
## subcategoryGeneral Topology 0.240451
## subcategoryGenetic and Genomic Medicine < 2e-16
## subcategoryGenetics < 2e-16
## subcategoryGenomics < 2e-16
## subcategoryGeometric Topology 0.013499
## subcategoryGeophysics 0.404865
## subcategoryGeriatric Medicine 0.472186
## subcategoryGraphics 0.542557
## subcategoryGroup Theory 0.592039
## subcategoryHardware Architecture 0.042249
## subcategoryHealth Economics 0.245065
## subcategoryHealth Informatics < 2e-16
## subcategoryHealth Policy 3.66e-13
## subcategoryHealth Systems and Quality Improvement < 2e-16
## subcategoryHematology 0.002615
## subcategoryHigh Energy Astrophysical Phenomena 4.06e-06
## subcategoryHigh Energy Physics - Experiment 0.007734
## subcategoryHigh Energy Physics - Lattice 5.22e-10
## subcategoryHigh Energy Physics - Phenomenology 0.963362
## subcategoryHigh Energy Physics - Theory 1.91e-07
## subcategoryHistory and Overview 0.199827
## subcategoryHistory and Philosophy of Physics 0.028531
## subcategoryHIV/AIDS 5.82e-16
## subcategoryHuman-Computer Interaction 6.63e-15
## subcategoryImage and Video Processing 0.000307
## subcategoryImmunology < 2e-16
## subcategoryInfectious Diseases (except HIV/AIDS) < 2e-16
## subcategoryInformation Retrieval 2.14e-07
## subcategoryInformation Theory 0.013735
## subcategoryInstrumentation and Detectors 0.585063
## subcategoryInstrumentation and Methods for Astrophysics 3.60e-05
## subcategoryIntensive Care and Critical Care Medicine 2.32e-13
## subcategoryK-Theory and Homology 0.000607
## subcategoryLogic 5.21e-07
## subcategoryLogic in Computer Science 0.003316
## subcategoryMachine Learning 0.615570
## subcategoryMaterials Science 0.003421
## subcategoryMathematical Finance 0.332773
## subcategoryMathematical Physics 2.62e-08
## subcategoryMathematical Software 0.008460
## subcategoryMedical Education 0.125946
## subcategoryMedical Physics 3.43e-07
## subcategoryMesoscale and Nanoscale Physics 0.495469
## subcategoryMethodology 1.85e-07
## subcategoryMetric Geometry 0.013130
## subcategoryMicrobiology < 2e-16
## subcategoryMolecular Biology < 2e-16
## subcategoryMolecular Networks 1.16e-07
## subcategoryMultiagent Systems 0.847608
## subcategoryMultimedia 0.000143
## subcategoryNephrology 1.41e-10
## subcategoryNetworking and Internet Architecture 0.432400
## subcategoryNeural and Evolutionary Computing 0.149886
## subcategoryNeurology < 2e-16
## subcategoryNeurons and Cognition 7.71e-11
## subcategoryNeuroscience < 2e-16
## subcategoryNuclear Experiment 0.007441
## subcategoryNuclear Theory 0.594553
## subcategoryNumber Theory 0.027731
## subcategoryNumerical Analysis 0.620556
## subcategoryNutrition 2.31e-10
## subcategoryObstetrics and Gynecology 1.54e-15
## subcategoryOccupational and Environmental Health < 2e-16
## subcategoryOncology < 2e-16
## subcategoryOperating Systems 0.110479
## subcategoryOperator Algebras 0.007543
## subcategoryOphthalmology 3.26e-11
## subcategoryOptics 0.865985
## subcategoryOptimization and Control 0.745342
## subcategoryOther Computer Science 0.278179
## subcategoryOther Condensed Matter 0.051473
## subcategoryOther Quantitative Biology 0.008574
## subcategoryOther Statistics 0.001371
## subcategoryOtolaryngology 0.090702
## subcategoryPaleontology 0.449530
## subcategoryPathology < 2e-16
## subcategoryPattern Formation and Solitons 0.339072
## subcategoryPediatrics < 2e-16
## subcategoryPerformance 0.239433
## subcategoryPharmacology and Therapeutics 4.38e-14
## subcategoryPharmacology and Toxicology < 2e-16
## subcategoryPhysics and Society 0.006868
## subcategoryPhysics Education < 2e-16
## subcategoryPhysiology < 2e-16
## subcategoryPlant Biology < 2e-16
## subcategoryPlasma Physics 0.002026
## subcategoryPopular Physics 0.038500
## subcategoryPopulations and Evolution 4.69e-13
## subcategoryPortfolio Management 0.308733
## subcategoryPricing of Securities 0.009299
## subcategoryPrimary Care Research 6.39e-07
## subcategoryProbability 0.216444
## subcategoryProgramming Languages 0.000475
## subcategoryPsychiatry and Clinical Psychology < 2e-16
## subcategoryPublic and Global Health < 2e-16
## subcategoryQuantitative Methods 7.14e-16
## subcategoryQuantum Algebra 0.855693
## subcategoryQuantum Gases 0.008740
## subcategoryQuantum Physics 0.055078
## subcategoryRadiology and Imaging < 2e-16
## subcategoryRehabilitation Medicine and Physical Therapy < 2e-16
## subcategoryRepresentation Theory 0.060738
## subcategoryRespiratory Medicine < 2e-16
## subcategoryRheumatology < 2e-16
## subcategoryRings and Algebras 0.000233
## subcategoryRisk Management 0.657232
## subcategoryRobotics 0.136030
## subcategoryScientific Communication and Education < 2e-16
## subcategorySexual and Reproductive Health < 2e-16
## subcategorySignal Processing 0.023359
## subcategorySocial and Information Networks 4.43e-06
## subcategorySoft Condensed Matter 0.034041
## subcategorySoftware Engineering 0.750289
## subcategorySolar and Stellar Astrophysics 7.59e-14
## subcategorySound 0.142480
## subcategorySpace Physics 0.027261
## subcategorySpectral Theory 0.554622
## subcategorySports Medicine 0.210545
## subcategoryStatistical Finance 0.869815
## subcategoryStatistical Mechanics 9.76e-06
## subcategoryStatistics Theory 0.004013
## subcategoryStrongly Correlated Electrons 0.061475
## subcategorySubcellular Processes 0.000230
## subcategorySuperconductivity 0.924663
## subcategorySurgery 0.002257
## subcategorySymbolic Computation 0.147432
## subcategorySymplectic Geometry 0.386400
## subcategorySynthetic Biology < 2e-16
## subcategorySystems and Control 0.100511
## subcategorySystems Biology < 2e-16
## subcategoryTheoretical Economics 0.008219
## subcategoryTissues and Organs < 2e-16
## subcategoryTrading and Market Microstructure 0.284828
## subcategoryZoology < 2e-16
##
## (Intercept) ***
## month ***
## covidTRUE ***
## covidpaperTRUE ***
## subcategoryAdaptation and Self-Organizing Systems
## subcategoryAddiction Medicine ***
## subcategoryAlgebraic Geometry
## subcategoryAlgebraic Topology
## subcategoryAllergy and Immunology ***
## subcategoryAnalysis of PDEs *
## subcategoryAnimal Behavior and Cognition ***
## subcategoryApplications ***
## subcategoryApplied Physics *
## subcategoryArtificial Intelligence .
## subcategoryAstrophysics of Galaxies ***
## subcategoryAtmospheric and Oceanic Physics
## subcategoryAtomic and Molecular Clusters
## subcategoryAtomic Physics *
## subcategoryAudio and Speech Processing *
## subcategoryBiochemistry ***
## subcategoryBioengineering ***
## subcategoryBioinformatics ***
## subcategoryBiological Physics ***
## subcategoryBiomolecules ***
## subcategoryBiophysics ***
## subcategoryCancer Biology ***
## subcategoryCardiovascular Medicine ***
## subcategoryCategory Theory
## subcategoryCell Behavior ***
## subcategoryCell Biology ***
## subcategoryChaotic Dynamics
## subcategoryChemical Physics
## subcategoryClassical Analysis and ODEs
## subcategoryClassical Physics .
## subcategoryClinical Trials ***
## subcategoryCombinatorics **
## subcategoryCommutative Algebra *
## subcategoryComplex Variables *
## subcategoryComputation
## subcategoryComputation and Language ***
## subcategoryComputational Complexity ***
## subcategoryComputational Engineering, Finance, and Science
## subcategoryComputational Finance *
## subcategoryComputational Geometry .
## subcategoryComputational Physics **
## subcategoryComputer Science and Game Theory
## subcategoryComputer Vision and Pattern Recognition **
## subcategoryComputers and Society ***
## subcategoryCosmology and Nongalactic Astrophysics ***
## subcategoryCryptography and Security
## subcategoryData Analysis, Statistics and Probability
## subcategoryData Structures and Algorithms *
## subcategoryDatabases *
## subcategoryDermatology **
## subcategoryDevelopmental Biology ***
## subcategoryDifferential Geometry .
## subcategoryDigital Libraries ***
## subcategoryDiscrete Mathematics
## subcategoryDisordered Systems and Neural Networks
## subcategoryDistributed, Parallel, and Cluster Computing
## subcategoryDynamical Systems
## subcategoryEarth and Planetary Astrophysics ***
## subcategoryEcology ***
## subcategoryEconometrics *
## subcategoryEconomics
## subcategoryEmergency Medicine ***
## subcategoryEmerging Technologies .
## subcategoryEndocrinology (including Diabetes Mellitus and Metabolic Disease) ***
## subcategoryEpidemiology ***
## subcategoryEvolutionary Biology ***
## subcategoryExactly Solvable and Integrable Systems
## subcategoryFluid Dynamics ***
## subcategoryFormal Languages and Automata Theory
## subcategoryFunctional Analysis
## subcategoryGastroenterology ***
## subcategoryGeneral Economics
## subcategoryGeneral Finance
## subcategoryGeneral Literature
## subcategoryGeneral Mathematics
## subcategoryGeneral Physics *
## subcategoryGeneral Relativity and Quantum Cosmology
## subcategoryGeneral Topology
## subcategoryGenetic and Genomic Medicine ***
## subcategoryGenetics ***
## subcategoryGenomics ***
## subcategoryGeometric Topology *
## subcategoryGeophysics
## subcategoryGeriatric Medicine
## subcategoryGraphics
## subcategoryGroup Theory
## subcategoryHardware Architecture *
## subcategoryHealth Economics
## subcategoryHealth Informatics ***
## subcategoryHealth Policy ***
## subcategoryHealth Systems and Quality Improvement ***
## subcategoryHematology **
## subcategoryHigh Energy Astrophysical Phenomena ***
## subcategoryHigh Energy Physics - Experiment **
## subcategoryHigh Energy Physics - Lattice ***
## subcategoryHigh Energy Physics - Phenomenology
## subcategoryHigh Energy Physics - Theory ***
## subcategoryHistory and Overview
## subcategoryHistory and Philosophy of Physics *
## subcategoryHIV/AIDS ***
## subcategoryHuman-Computer Interaction ***
## subcategoryImage and Video Processing ***
## subcategoryImmunology ***
## subcategoryInfectious Diseases (except HIV/AIDS) ***
## subcategoryInformation Retrieval ***
## subcategoryInformation Theory *
## subcategoryInstrumentation and Detectors
## subcategoryInstrumentation and Methods for Astrophysics ***
## subcategoryIntensive Care and Critical Care Medicine ***
## subcategoryK-Theory and Homology ***
## subcategoryLogic ***
## subcategoryLogic in Computer Science **
## subcategoryMachine Learning
## subcategoryMaterials Science **
## subcategoryMathematical Finance
## subcategoryMathematical Physics ***
## subcategoryMathematical Software **
## subcategoryMedical Education
## subcategoryMedical Physics ***
## subcategoryMesoscale and Nanoscale Physics
## subcategoryMethodology ***
## subcategoryMetric Geometry *
## subcategoryMicrobiology ***
## subcategoryMolecular Biology ***
## subcategoryMolecular Networks ***
## subcategoryMultiagent Systems
## subcategoryMultimedia ***
## subcategoryNephrology ***
## subcategoryNetworking and Internet Architecture
## subcategoryNeural and Evolutionary Computing
## subcategoryNeurology ***
## subcategoryNeurons and Cognition ***
## subcategoryNeuroscience ***
## subcategoryNuclear Experiment **
## subcategoryNuclear Theory
## subcategoryNumber Theory *
## subcategoryNumerical Analysis
## subcategoryNutrition ***
## subcategoryObstetrics and Gynecology ***
## subcategoryOccupational and Environmental Health ***
## subcategoryOncology ***
## subcategoryOperating Systems
## subcategoryOperator Algebras **
## subcategoryOphthalmology ***
## subcategoryOptics
## subcategoryOptimization and Control
## subcategoryOther Computer Science
## subcategoryOther Condensed Matter .
## subcategoryOther Quantitative Biology **
## subcategoryOther Statistics **
## subcategoryOtolaryngology .
## subcategoryPaleontology
## subcategoryPathology ***
## subcategoryPattern Formation and Solitons
## subcategoryPediatrics ***
## subcategoryPerformance
## subcategoryPharmacology and Therapeutics ***
## subcategoryPharmacology and Toxicology ***
## subcategoryPhysics and Society **
## subcategoryPhysics Education ***
## subcategoryPhysiology ***
## subcategoryPlant Biology ***
## subcategoryPlasma Physics **
## subcategoryPopular Physics *
## subcategoryPopulations and Evolution ***
## subcategoryPortfolio Management
## subcategoryPricing of Securities **
## subcategoryPrimary Care Research ***
## subcategoryProbability
## subcategoryProgramming Languages ***
## subcategoryPsychiatry and Clinical Psychology ***
## subcategoryPublic and Global Health ***
## subcategoryQuantitative Methods ***
## subcategoryQuantum Algebra
## subcategoryQuantum Gases **
## subcategoryQuantum Physics .
## subcategoryRadiology and Imaging ***
## subcategoryRehabilitation Medicine and Physical Therapy ***
## subcategoryRepresentation Theory .
## subcategoryRespiratory Medicine ***
## subcategoryRheumatology ***
## subcategoryRings and Algebras ***
## subcategoryRisk Management
## subcategoryRobotics
## subcategoryScientific Communication and Education ***
## subcategorySexual and Reproductive Health ***
## subcategorySignal Processing *
## subcategorySocial and Information Networks ***
## subcategorySoft Condensed Matter *
## subcategorySoftware Engineering
## subcategorySolar and Stellar Astrophysics ***
## subcategorySound
## subcategorySpace Physics *
## subcategorySpectral Theory
## subcategorySports Medicine
## subcategoryStatistical Finance
## subcategoryStatistical Mechanics ***
## subcategoryStatistics Theory **
## subcategoryStrongly Correlated Electrons .
## subcategorySubcellular Processes ***
## subcategorySuperconductivity
## subcategorySurgery **
## subcategorySymbolic Computation
## subcategorySymplectic Geometry
## subcategorySynthetic Biology ***
## subcategorySystems and Control
## subcategorySystems Biology ***
## subcategoryTheoretical Economics **
## subcategoryTissues and Organs ***
## subcategoryTrading and Market Microstructure
## subcategoryZoology ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 60104.1 on 3472 degrees of freedom
## Residual deviance: 5088.7 on 3258 degrees of freedom
## AIC: 24195
##
## Number of Fisher Scoring iterations: 4
Ojo que ahora esto son odds ratio! Podemos transformar el intercept a la unidad original:
exp(coef(fit_glm)[1]) / (exp(coef(fit_glm)[1]) + 1)
## (Intercept)
## 0.8570044
No está mal. Quizás un poco alto. Y los efectos:
sjPlot::plot_model(fit_glm)
Y ya todo junto: binomial fraccional de efectos mixtos. Hay que escalar el mes o si no se queja (también se puede cambiar por el año, no hay mucha diferencia):
fit_glmer <- glmer(
r_male ~ scale(month, FALSE) + covid + covidpaper + (1 | category/subcategory),
df.agg, family=binomial, weights=total)
Tenemos:
model_performance(fit_glmer)
## `geom_smooth()` using formula 'y ~ x'
## pseudo-R2 = 0.79687
Similar, y:
model_assumptions(fit_glmer)
## `geom_smooth()` using formula 'y ~ x'
Similar. Finalmente:
summary(fit_glmer)
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: binomial ( logit )
## Formula:
## r_male ~ scale(month, FALSE) + covid + covidpaper + (1 | category/subcategory)
## Data: df.agg
## Weights: total
##
## AIC BIC logLik deviance df.resid
## 24734.5 24771.4 -12361.3 24722.5 3467
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.5921 -0.8027 0.0669 0.8833 6.0866
##
## Random effects:
## Groups Name Variance Std.Dev.
## subcategory:category (Intercept) 0.05536 0.2353
## category (Intercept) 0.18635 0.4317
## Number of obs: 3473, groups: subcategory:category, 219; category, 8
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.507958 0.154624 9.752 < 2e-16 ***
## scale(month, FALSE) -0.094377 0.005458 -17.290 < 2e-16 ***
## covidTRUE 0.020527 0.005823 3.525 0.000423 ***
## covidpaperTRUE 0.072710 0.015417 4.716 2.4e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) s(,FAL covdTRUE
## scl(,FALSE) -0.030
## covidTRUE 0.010 -0.620
## covdpprTRUE -0.004 0.002 -0.128
Esta es la estimación del intercept más ajustada hasta ahora:
exp(fixef(fit_glmer)[1]) / (exp(fixef(fit_glmer)[1]) + 1)
## (Intercept)
## 0.8187583
Nice! Efectos fijos:
sjPlot::plot_model(fit_glmer) + ylim(0.7, 1.3)
## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.
Y siguen saliendo positivos. Lo que me escama es que se ve una bajada en las gráficas de arriba. La media de la proporción de hombres para 2020 es más baja, pero las variables COVID salen siempre positivas (!). ¿Por qué?
Efectos aleatorios:
sjPlot::plot_model(fit_glmer, "re")[[2]]
sjPlot::plot_model(fit_glmer, "re")[[1]]
¿Qué pasa si usamos categorías (demasiado gruesas) más otra variable predictiva (la que nos hemos dejado todo este rato)?
fit_glmer2 <- glmer(
r_male ~ scale(month, FALSE) + covid + covidpaper + diss + (1 | category),
df.agg, family=binomial, weights=total)
Esto es interesante:
model_performance(fit_glmer2)
## `geom_smooth()` using formula 'y ~ x'
## pseudo-R2 = 0.7022666
Siguen saliendo dos modos, dos clusters, pero se explica bastante más variabilidad.
model_assumptions(fit_glmer2)
## `geom_smooth()` using formula 'y ~ x'
Los residuales siguen siendo fetén, porque el problema es el tipo de modelo (binomial fraccional vs. gaussiano). ¿Adivináis qué pasa con los coeficientes COVID?
summary(fit_glmer2)
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: binomial ( logit )
## Formula: r_male ~ scale(month, FALSE) + covid + covidpaper + diss + (1 |
## category)
## Data: df.agg
## Weights: total
##
## AIC BIC logLik deviance df.resid
## 27854.5 27891.4 -13921.3 27842.5 3467
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.5889 -1.0988 -0.0062 1.0450 5.0789
##
## Random effects:
## Groups Name Variance Std.Dev.
## category (Intercept) 0.04472 0.2115
## Number of obs: 3473, groups: category, 8
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.388100 0.076254 5.090 3.59e-07 ***
## scale(month, FALSE) -0.091253 0.005415 -16.851 < 2e-16 ***
## covidTRUE 0.020280 0.005797 3.498 0.000469 ***
## covidpaperTRUE 0.063838 0.013987 4.564 5.02e-06 ***
## diss 1.942396 0.023573 82.400 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) s(,FAL covdTRUE cvdpTRUE
## scl(,FALSE) -0.065
## covidTRUE 0.025 -0.625
## covdpprTRUE -0.011 0.011 -0.139
## diss -0.173 0.022 -0.015 -0.001
Siguen saliendo positivos. Lo que pasa ahora es que el índice de disimilaridad se ha llevado medio intercept (!).